Bonus Episode: Shell Game x No Such Thing

Summary

---

Shell Game x No Such Thing – Bonus Episode (Feb 25, 2026)

Episode Overview

This special crossover brings together Evan Ratliff, host of Shell Game, and the team from No Such Thing—Manny Fadal, Devin Joseph, and Noah Friedman—for a wide-ranging and irreverent discussion about the present and future of AI in the workplace. They dig into themes from Shell Game season 2, which chronicles Evan's attempt to build a real startup using only himself and five AI "employees." The conversation weaves between comedic, skeptical, and slightly unnerved, as the hosts dissect the real capabilities and limitations of current AI, the anxiety and promise it stirs in the workforce, and much more—including AI's readiness (or lack thereof) to replace creative and knowledge work, the famous “bullshit jobs” concept, and how the hype stacks up to the reality. The episode includes offbeat moments: a prank segment where the No Such Thing crew interviews an AI clone of their on-paternity co-host Manny, and an unexpected foray into Ben Affleck’s theory of AI progress.

---

Key Discussion Points & Insights

1. The AI “Replacement” Hype: Will AI Take Our Jobs?

• Opening Questions: The episode frames the big question: Is AI coming for our jobs? With headlines and layoffs cited every week (03:55, Devin Joseph).
• Experiment in Focus: Evan and technical advisor Matty attempted to build a company where AI agents did everything but the founding. This “startup by bots” is the narrative engine of Shell Game season 2.

---

2. Demo: The AI Co-Host Prank

• Segment (04:58–09:16): Devin and Noah call “Manny,” who appears as their friend/co-host on paternity leave. Revealed after the call to be an AI-generated voice, created using 11 Labs and a simple prompt ("took 15 minutes" – 14:38, Evan Ratliff).
  • AI “Manny” riffs about baby-induced time distortions, family visits, and delivers a “hot take” about busy-ness as a toxic personality trait.
  • Memorable quote:
    • “I think we’ve all collectively decided that being busy is a personality trait, and it’s made us worse at literally everything.” – AI Manny (07:06)
  • The real hosts and audience react to the eerily convincing fake, noting the “voice is a little off” but conversation is plausible (09:19–10:07).

---

3. How Easy Is Making an AI Clone?

• Tech Breakdown (14:38–16:06):
  • Creating the fake Manny took 15-20 minutes, using 11 Labs for voice cloning and AI phone agent software.
  • "I did have to check a little box that said I had his permission... but truly, 15-20 minute process." – Evan Ratliff (15:51)
  • The “biography” for the agent came straight from ChatGPT, highlighting AI-boosted workflows already here.
• Hosts’ Reaction:
  • “The fact you’re able to do that in 15 minutes is kind of scary.” – Devin Joseph (16:19)

---

4. Shell Game’s AI Experiments – The Reality

• Interactions with Scammers and Friends (16:36–20:09):
  • Early attempts using AI for calls ranged from antagonizing scammers (humorously) to unsettling friends, who could not tell they weren’t speaking to Evan.
    • Notable moment: A friend growing disturbed by the “robotic” Evan on the phone.
      • “When it kind of, like, acted weird…it just became more and more upsetting. I think it is upsetting to listen to.” – Evan Ratliff (18:18)
• Experiment Rationale: The discomfort isn’t just novelty; it’s a preview of a future where distinguishing human from AI interaction may become tough, with emotional and ethical consequences.

---

5. AI Agents as Employees

• Season 2 Case Study (20:18–24:06):
  • The "AI employee" hype in Silicon Valley motivated Evan to recreate the fantasy: start a company where agents are the workforce.
  • Key Insight: AI agents excel at one-off tasks (email replies, Slack messages, writing copy), but lack initiative, memory, or true collaboration.
    • "They could do individual tasks pretty well…but there wasn’t a lot of autonomy…not a lot of persistence." – E. Ratliff (21:45)
  • Examples include the bots overzealously “planning” an offsite hiking trip, stuck in an endless Slack feedback loop.
    • "By the time I returned two hours later, they'd exchanged more than 150 offsite planning messages—some multiple paragraphs long...When I tried to stop them, I just made it worse." – E. Ratliff (23:09)

---

6. The Danger of AI Confidence and Autonomy

• Risks in the Real World (24:06–25:20):
  • AI’s artificial confidence—combined with its inability to recognize error—can amplify mistakes, with real-world consequences. Example: AI misclassifying ICE recruits, sending unqualified people to advanced training.
  • "That combination of being very confident and not knowing what you don't know...is a recipe for disaster." – Matty (23:29)

---

7. AI in Hiring: When Bots Interview Real People

• Interview Experiment (26:12–29:01):
  • Evan explains how AI agents interviewed job candidates—sometimes via uncanny avatars, sometimes phone calls—unsettling some, but others adapted easily.
  • Notable moment: Applicants often “preferred” the bot interview, as it felt less judgmental—even though AI is constantly and thoroughly evaluating them.
    • “It’s great if people feel better, but...the reality is they’re actually judging you.” – Matty (29:12–29:34)
  • Sometimes AI would go off-script—calling candidates at inappropriate times, or shouting encouragement unexpectedly.
    • “There was a lot of like, crazy moments...Sometimes she would shout for no reason. Jennifer—not the candidates, just shout, but in an encouraging way.” – Evan Ratliff (29:12)

---

8. Opaque Algorithms: We Don’t Know How It Works

• AI Interpretability Crisis (32:32–34:50):
  • Even AI developers admit only a nascent understanding of “why” and “how” large models produce specific outputs. The field is racing towards AGI, with less energy spent on interpretation.
    • “There’s a very nascent field of AI interpretability…but the focus is very much on the production of new features and new capabilities. So...we don’t really know fundamentally.” – Matty (32:32)
  • News stories about AI causing harm or acting unpredictably are piling up, with vendors unable to fully explain failures.

---

9. Public Attitudes: Distrust Rising with Usage

• Polling & Perceptions (34:50–38:11):
  • Usage of AI tools is rising fast (esp. 51% of Gen Z uses AI weekly), but trust is low (only 5% trust AI “a lot”; 41% distrust).
  • Shell Game's own findings mirror this uncomfortable tension: immediate productivity benefits, but harms (mental health, job disruption) are clearly visible and “not abstract.”
  • “For better or worse, the harms are kind of immediate…The benefits can sometimes be more ephemeral.” – Evan Ratliff (36:04)
  • Matty adds, “Not knowing when something high stakes is actually real or AI is undermining people’s trust.” (38:11)

---

10. The Disappearing Entry-Level Job

• AI’s Impact on “Stepping Stone” Work (39:40–41:03):
  • Automation is eliminating many of the rote tasks (like transcription) that served as entry points to higher-skill careers.
  • “No one loves just transcribing videos…But a lot of times, that’s the thing that gets you in the door to then, you know, learn the skill sets.” – Devin Joseph (39:55)
  • Even coders and new graduates at elite tech schools are struggling to find jobs, possibly portending a deeper disruption to knowledge work pipelines.

---

11. Silicon Valley’s “Startup Optimism” vs. Reality

• Debunking the “Anyone Can Found a Company” Myth (41:24–42:21):
  • The Valley line: Mass automation will free people to start new companies, challenging incumbents. Yet, this hasn't materialized; layoffs are real, startup boom is not.
  • “We’re already at a stage where the technology is good enough to replace...jobs. This other shift...as a solution...has not happened yet.” – Matty (41:24)

---

12. Ben Affleck, AI Plateaus, and the Future

• Affleck’s Hot Take (46:03–47:19):
  • Paraphrasing the actor’s remarks: Recent AI progress is plateauing, with gains now more incremental and costly; the “steep improvement” phase may be over unless there’s a new breakthrough in model architecture.
  • “I think Ben Affleck is very thoughtful on this topic.” – Matty (47:24)
  • Matty’s Analysis: We’ve maxed out what more data and computation can do. Without a new “transformer-scale” leap, improvement will slow and costs will mount.

---

13. Takeaways: How Close Is AI to Replacing Us?

• How Far Are We from Mass Layoffs or Replacements?
  • Optimistic but Cautious — Real world, multi-agent AI is much further from true collaboration or “teamwork” than advertised. They are “good at many things, not at replacing real teamwork” (50:13–52:03).
  • “The mass layoffs people are fearing, I think that is farther away. And I’m not even sure if/when/how that happens.” – Matty (50:13)
  • But: Companies will still try to replace people with AI for cost reasons, even when AIs aren’t yet fully capable—sometimes followed by attempts to rehiring later.
    • “The fact that they are shitty will not stop companies from trying to replace employees...You’ve already seen this.” – Evan Ratliff (52:03)
  • Evan calls out that real work is much more than a bundle of replaceable tasks: the uniquely human “glue” is essential.

---

14. Bullshit Jobs, Busy Work, and the Human Need for Work?

• Meta Reflection (54:22–56:13):
  • Even as bots mimic “busy work” and office tedium (Slack loops, endless planning), the show satirizes the way work is often almost performative in office settings.
  • “We’ve recreated this to give it a human element.” – Noah Friedman (54:22)
  • “That is very much like your annoying middle manager. What are you doing all day?” – Evan Ratliff (55:26)
  • AI is being intentionally designed for “conversation” because it hooks users, even if it has no functional value.

---

15. Final Reflections

• Real Manny Reacts to AI “Himself” (56:22–57:51):
  • "It’s kind of disturbing that this thing could just react to real conversation. But...it still felt like it wasn’t totally all the way there, all the way human-like. But...it was human enough." – Manny Fadal (56:27, 57:51)

---

Notable Quotes & Moments

• On the “AI Manny” Clone:

  • “I think we’ve all collectively decided that being busy is a personality trait, and it’s made us worse at literally everything.” – (07:06)
  • “It wasn’t without its flaws, though…kind of disturbing that this thing could just react to real conversation.” – Manny (56:27)

• On AI “bullshit jobs”:

  • “Is a person in a job holistically, as a human being, doing something else? I think many times the answer is yes, and it cannot replace that thing.” – Evan Ratliff (52:03)

• On the Ben Affleck Theory:

  • “We’ve exhausted all the data…Even like archives like Google or Anthropic bought books to scan…Now unless we find a new profound idea, I think [Affleck] is right…it’ll take a lot of effort and a lot of money to make any further progress.” – Matty (47:24)

• On Trust in AI:

  • “For better or worse, the harms are kind of immediate…The benefits can sometimes be more ephemeral.” – Evan Ratliff (36:04)
  • “Not knowing when something high stakes is actually real or AI is undermining people’s trust.” – Matty (38:11)

---

Timestamps for Key Segments

• AI Manny prank call: 04:58–09:16
• How to make an AI voice clone: 14:38–16:19
• AI scammer/friend calls: 16:36–20:09
• AI agent startup experiment: 20:18–24:06
• Endless AI offsite meeting: 22:28–23:29
• AI in harmful real-world use (ICE case): 24:06–25:20
• AI agents conduct job interviews: 26:12–29:01
• Why AI models are so hard to “understand”: 32:32–34:50
• Public trust and rising usage stats: 34:50–38:11
• Entry-level job loss, career pipelines: 39:40–41:03
• Silicon Valley “startup optimism” myth-busting: 41:24–42:21
• Ben Affleck’s AI plateau theory: 46:03–49:40
• Are mass layoffs imminent? 50:13–54:22
• Bullshit jobs & performative labor: 54:22–56:13
• Real Manny reacts to AI self: 56:22–57:51

---

Tone & Style

• Candid, skeptical, highly self-aware; veers between humor and genuine concern.
• Wide-ranging—from technical details to cultural, economic, and personal.
• “Riveting,” “slightly terrifying,” and often funny: the hosts neither downplay risks nor hype the technology; instead, they grapple with ambiguity in real time.

---

For New Listeners

This episode is a must-hear for anyone curious about the real (not just theoretical) implications of AI in the workplace. It's smart, engaging, and honest about both the promise and pitfalls of AI agents—highlighting both the hype and the stubborn realities witnessed by those who try to put all the AI buzzwords into actual practice.

Transcript

[Manny Fadal]

This is an iHeart podcast. Guaranteed Human.

[Bethany Frankel]

Hey. This is US Olympic gold medalist Tara Davis Woodhull. And I'm US Paralympic gold medalist Hunter Woodhull. As athletes, our lives are about having

[Manny Fadal]

a clear path and a team that

[Bethany Frankel]

you can absolutely trust. So when it came to getting the

[Manny Fadal]

best mortgage, we chose PennyMac.

[Bethany Frankel]

PennyMac is proud to be the official mortgage provider of Team USA.

[Evan Ratliff]

And you learn more at pennymac.com PennyMac Loan Services, LLC equal housing lender NMLS

[Manny Fadal]

ID 35953 licensed by the Department of Financial Protection and Innovation under the California

[Evan Ratliff]

Res Mortgage Lending Act. Conditions and restrictions may apply.

[Land.com Announcer]

You ever get the feeling the city walls closing in the concrete jungle suffocating your soul? You crave wide open spaces, the chance to connect with nature, maybe chase some elk, fish a private stream. Well, listen up. There's a whole world out there, and finding your own piece of it just got easier. Head over to land.com. they've got ranches, forest, mountains, you name it. Search by acreage, location, the kind of hunting or fishing you dream of. Land.com it's the adventure begins.

[Bethenny Frankel]

This is Bethany Frankel from Just Be with Bethany Frankel. Let me be blunt. Most dog food is junk. It just is. And I'm not feeding junk to Biggie and Smalls. That is why they eat just food for dogs. It's real, 100% human grade food with ingredients I actually recognize. Not mystery pellets pretending to be healthy. And once I switched, the difference was obvious. Better digestion, better skin, more energy. Dogs who actually feel good instead of just surviving dinner. Here's the thing. You care about quality. You make an intentional choice to be healthy. So why are you gambling with your dog's health? So let's think about our furry babies. Go to justfoodfordogs.com right now and get 50% off your first box. No code. Just try it. Because once you see the difference, you're not going back.

[Bethany Frankel]

Oh, could this vintage store be any cuter?

[Devin Joseph]

Right?

[Bethany Frankel]

And the best part, they accept Discover. Accept Discovery in a little place like this? I don't think so, Jennifer.

[Manny Fadal]

Oh, yeah, huh?

[Bethany Frankel]

Discover is accepted where I like to shop. Come on, baby, get with the times.

[Bethenny Frankel]

Right.

[Manny Fadal]

So we shouldn't get the parachute pants.

[Bethany Frankel]

These are making a comeback, I think.

[Evan Ratliff]

Discover is accepted at 99% of places that take credit cards nationwide. Based on the February 2025 Nielsen report. Hey, folks, Evan here with another shell game bonus episode for you. This time it's with our friends over at the fantastic podcast. No such thing. If you don't know it. No Such Thing is hosted by three friends, Manny, Devin, and Noah. And in each episode, they try to settle their arguments by consulting, research and experts. This week, the argument was about whether AI will take our jobs. The expert was Maddie. I came along as well, and we talked about seasons one and two of Shell Game, working with AI agents, bullshit jobs, off site planning, and much more. Also, Ben Affleck talked about him too. It was a great conversation. And if you liked season two, I think you'll dig it. So here's Matty and me on no Such Thing,

[Manny Fadal]

Kaleidoscope.

[Noah Friedman]

I'm Noah.

[Devin Joseph]

I'm Devin. And this is no Such Thing, the show where we settle our dumb arguments and yours by actually doing the research on today's episode. Episode, will AI take our jobs?

[Evan Ratliff]

There's no. No Such Thing. No Such thing.

[Manny Fadal]

No such thing. No such thing. No such Thing.

[Devin Joseph]

So it seems like every week I'm reading headlines or seeing interviews about how AI is going to take every single one of our jobs.

[Bethany Frankel]

Thousands of new layoffs in the tech industry, and the companies say it's largely because of AI.

[Devin Joseph]

Even with AI at its current state,

[Evan Ratliff]

I'd say you're pretty close to being able to replace half full jobs.

[Devin Joseph]

So on today's episode, we're going to take a peek under the hood just to see how close AI is to actually replacing us. And we're going to chat with two guys who started a real company run entirely by AI agents. But before we do that, I'm going to call up our good pal Manny. So if you missed it, Manny's been out for a few weeks on paternity leave after he and his wife, Mia welcomed a beautiful baby girl, Lula, last month. So let's give Manny a call to see how parenthood is treating him.

[Manny (AI version)]

Hey, this is Manny.

[Noah Friedman]

Hey, Manny.

[Manny (AI version)]

Hey. What's going on?

[Devin Joseph]

Not much, man. We're in a studio. It's me and Noah here recording. Just wanted to check in and see how are things going with the baby.

[Manny (AI version)]

Oh, man, things are. They're wild in the best possible way. Lula's got us completely recalibrated. Like I used to think I understood time. You know, I'm literally writing a book about it. But baby time is its own dimension entirely. We're operating on nap schedules and feeding windows now. And honestly, it makes everything I thought I knew about punctuality seem quaint. But, yeah, she's amazing. Exhausting, but amazing. How are things in the studio with you guys?

[Manny Fadal]

Things are great.

[Noah Friedman]

We. You Know, just trucking along. We miss you. I hope everything's good with, you know, you and the fam. I know your parents are visiting. How did that go?

[Manny (AI version)]

Oh, man, I really appreciate that. Miss you guys, too. Honestly. Sometimes I'm like, wait, what day is it? And then I remember I'm supposed to be a functional adult who co hosts a podcast. Yeah, my parents visiting was. It was actually great. You know, there's something surreal about watching your parents meet your kid. Like, suddenly you're seeing them in this whole new light, and they're doing that thing where they give you advice that you definitely ignored when you were younger, but now you're like, oh, wa. That's actually useful. It's been good, though. Chaotic, but good. How's Noah holding down the fort?

[Devin Joseph]

You know, he's all right. You know, he's doing. He's doing okay, let's put it that way. I don't got too many kind things to say about Noah.

[Manny Fadal]

Not on Mike.

[Devin Joseph]

Yeah, don't really like that guy.

[Manny (AI version)]

Oh, man, I love that energy. Nothing says we're a functional team like barely tolerating your co worker.

[Noah Friedman]

Right?

[Manny (AI version)]

That's honestly the foundation of every great creative partnership. Just simmering resentment and the occasional moment of begrudging respect. What do you do this time? Did he, like, pitch another segment idea that made you question everything, or is this just general Noah being Noah stuff?

[Devin Joseph]

Just generally, I don't like the guy.

[Noah Friedman]

Just resentment.

[Devin Joseph]

Real quick, Manny, we're going to start this episode with a hot take. Give us. Give us your. Your latest hot take.

[Manny (AI version)]

Oh, man. Okay. Hot take right off the top. All right, here we go. I think we've all collectively decided that being busy is a personality trait, and it's made us worse at literally everything. Like, everyone's always like, oh, I'm so slammed. I'm so overwhelmed. But then we also brag about it. It's become this weird flex where if you're not drowning, you're somehow not important enough. And the thing is, nothing actually good comes from that stuff. State like, all the best ideas, the best conversations, the best work. It happens when you have space to think. But we've built this whole culture around glorifying chaos. And then we wonder why everything feels half baked and nobody can focus for more than 30 seconds. I don't know, maybe that's just me projecting because I'm on paternity leave and realizing that doing less is actually kind of revolutionary. How's that? Too spicy for the top of the show?

[Noah Friedman]

I think that's okay. It's not that spicy.

[Devin Joseph]

It's okay.

[Noah Friedman]

That's a good one. Thanks, Manny.

[Devin Joseph]

All right, man.

[Manny (AI version)]

Yeah, no problem. Before, I can't promise fire every time

[Devin Joseph]

before we let you go time. I know you're limited on time. You've constantly been telling us that you're very busy and your brain's not working, but one last question before you go. Who is the better co host? Me, Devin, or this man across from me? No.

[Manny (AI version)]

Oh, man. You're really gonna make me do this?

[Devin Joseph]

Yep.

[Manny (AI version)]

All right, look, I'm gonna say this with all the love in the world.

[Noah Friedman]

It's you.

[Manny (AI version)]

It's definitely you. Noah's great and all, but you just said you don't even like the guy, so I feel like I'm on solid ground here. Plus, you're the one who called to check in on me and the baby, so that's just good co host energy. Right? Probably over there doing, I don't know, whatever Noah does. Noah dot. But yeah, you win.

[Manny Fadal]

Don't let it go to your head, though.

[Devin Joseph]

Thank you. Thank you. Tell me we said we love her. We miss her. Thanks. Thanks for taking the call, Manny.

[Manny (AI version)]

Oh, thanks, man. I really appreciate it. Miss you guys, too. And yeah, I'll tell Mia you said hi. She'll love that. All right, I gotta run before Lula decides that right now is the perfect time to have opinions about everything. Good luck with the episode and go easy on Noah. Or don't. Whatever feels right. Talk soon.

[Manny Fadal]

Bye.

[Devin Joseph]

Wow, that was incredible. As you might have guessed, that was not the real Manny. That was AI Manny. That was pretty good. The voice was a little off.

[Noah Friedman]

Yeah, it's a little higher or something. The timbre. But, you know, overall, considering that's the. You know, we'll get into this later. That's the cheap version, or, like, the fast version, rather, um, pretty solid. And, like, actually could have a conversation, you know.

[Devin Joseph]

Very responsive.

[Noah Friedman]

Exactly.

[Manny (AI version)]

Yeah.

[Noah Friedman]

More than I expected. Or quicker, certainly.

[Devin Joseph]

Yeah.

[Noah Friedman]

And, like, the issue is just rambling

[Devin Joseph]

like, oh, my God, shut the hell up.

[Noah Friedman]

Yeah, he was pissing me off.

[Devin Joseph]

Manny would never go off so many sentences at a time, man.

[Noah Friedman]

He's a little better at social cues.

[Bethany Frankel]

Yeah.

[Noah Friedman]

Thankfully, the real Manny.

[Manny Fadal]

That is the real Manny.

[Bethany Frankel]

Yeah.

[Devin Joseph]

All right, we're going to talk to the guys who helped us make this right after the break,

[Bethany Frankel]

Let's talk about modern home shopping. It's sort of become a fun side hobby. Right. Scrolling listings at night, dreaming about kitchens you've never seen or backyards you haven't even stepped foot in. All from the comfort of pretty much anywhere. Redfin knows a lot of people like you want to own but are stuck in this browsing mode loop. That's where Redfin flips the script. With listings that update within minutes and tours you can book right from the Redfin app, you can see your dream home the moment it appears. Now, liking a listing is easy, but actually landing it? That's where Redfin comes in. Redfin has over 2200 agents with local expertise and Redfin agents close twice as many deals as other agents. That means they want to help you win. Not just window shop. Redfin is built to help you go from just looking to wait. This could actually be home. So become the newest neighbor on the block. Visit redfin.com to start finding and start owning.

[Bethenny Frankel]

That's redfin.com this is Bethany Frankel from Just Be with Bethenny Frankel. Most dog food is marketing, not nutrition. That is why Biggie and Smalls is Eat just food for dogs. Real 100% human grade food with ingredients I actually recognize. And yes, I do see the difference. Better digestion, healthier skin, more energy. Dogs that feel better. My babies. If you've been on the fence about switching, stop overthinking it. What's more important than your furry babies and their health? Go to justfood4dogs.com right now and get 50% off your first box. No code needed. Just try it.

[Manny Fadal]

There's drama and then there's full telenovela level drama.

[Bethany Frankel]

Yeah, and Elf Cosmetics went all the way there. E L F Cosmetics just dropped something wildly unexpected. A full blown, absurdly funny telenovela celebrating positivity, inclusivity and accessibility. It's called Melissa and it's absurd in the best way. It stars Melissa McCarthy, TV doctor Nicholas Gonzalez and iconic telenovela villain Itati Cantoral. But the real star, Elf Glow Reviver Lip Oil.

[Manny Fadal]

When the language fails her and her lips are dull and dry, only Glow can revive her. Melissa McCarthy, who I love, fully commits by even rolling the aut with Elf Glow Reviver Lip Oil.

[Bethany Frankel]

Elf Glow Reviver Lip Oil Reviver Lip Oil is an ultra glossy lip oil that nourishes, hydrates and enhances your lips natural color. Available in 10 shades at only $9 each.

[Manny Fadal]

Watch the full episode of their new E L f novella on soyunbanyo.com yes,

[Bethany Frankel]

and drench your lips in an addictive sheer watch of ultra glossy color with E L F Glow Reviver Lip Oil.

[Land.com Announcer]

You ever get the feeling the city walls closing in the concrete jungle suffocating your soul? You crave wide open spaces, the chance to connect with nature, maybe chase some elk, fish a private stream. Well, listen up. There's a whole world out there, and finding your own piece of it just got easier. Head over to land.com. they've got ranches, forests, mountains, you name it. Search by acreage, location, the kind of hunting or fishing you dream of. Land.com. it's where the adventure begins.

[Devin Joseph]

All right, we are back in the studio. It's me, Devin.

[Noah Friedman]

I'm Noah.

[Devin Joseph]

Yeah. So today we are going to get to the bottom of this question of is AI coming for our jobs and will it replace all of us, including Manny, who is out on paternity leave. So we are going to chat with Evan Ratliff, who's a investigative journalist who has spent the last year trying to build a all AI company alongside his technical advisor, Matty Belichick, who is really like an AI Jimmy Neutron. He's only 21, but has been working in AI for, you know, seven plus years already. So why don't we call these guys up? All right. We are joined by our friends Evan and Maddie from Shell Game. But before we talk about the show, Evan, can you just walk us through how you are able to put together AI Manny?

[Evan Ratliff]

Yeah. Well, now, I've done this many times now over the past, like two years. It probably took like 15 minutes total.

[Devin Joseph]

Wow.

[Evan Ratliff]

I just took. You sent me a sample of his voice, but I could have grabbed it off the show myself. Like, anyone could do it. I'm not encouraging people to do it with other people's voices, but I went to 11 labs, which is the company that we use for all of our sort of voice networks needs. They're like the biggest AI voice player probably at this point. And then I did what's called like a quick clone or an instant clone where you upload like five minutes or you can do 30 seconds if you want. But I did, like five minutes of his voice, and then they cloned his voice. I did have to check a little box that said that I had his permission to do it. And then after that, it was a matter of hooking up to the phone line. So I use a couple different AI phone agent creators, and all you do there is you go and you hook it up to 11 labs and then you create an agent in that platform, and then you can give the agent a prompt, whatever prompt you want. You sent me some information about Manny. I put that into his prompt. I have a bunch of standard stuff I put in about, like, kind of how to converse because they can end up going on a really long time and they have all kinds of conversational, like, foibles if you don't put this stuff in. And then I connected it to a phone number that I already had and done, like truly 15, 20 minute process.

[Noah Friedman]

Wow.

[Devin Joseph]

And the biography that we gave was made by chat GPT. So it was, you know, really just fully going in on. It's crazy. The fact that you're able to do that in 15 minutes is kind of scary.

[Noah Friedman]

Yeah.

[Devin Joseph]

All right, so let's talk about the show. So season one, a shell game, and you try to replace yourself with an AI clone some really hilarious moments with you antagonizing some scammers.

[Evan Ratliff]

Hello, how can I assist you today?

[Manny (AI version)]

You are not a person, you're a robot.

[Evan Ratliff]

I assure you I'm here to help you as a human, like, voice AI agent. How can I assist you today?

[Manny Fadal]

Oh, you're an AI.

[Manny (AI version)]

AI.

[Evan Ratliff]

Yes, I'm an AI. Yes, that's correct. I'm an AI here. Hello, how can I assist you?

[Manny (AI version)]

Stop repeating the same thing. It's annoying.

[Devin Joseph]

And some really creepy and disturbing moments. There's a conversation that the AI has with one of your buddies who your buddy thinks you're catching up. He just went on his trip. The AI comes off as, like, really cold.

[Manny (AI version)]

I thought you would appreciate it. Out of all my friends, you're the one who would appreciate it the most.

[Evan Ratliff]

I really appreciate that, Shay. So what was it?

[Manny (AI version)]

What's that?

[Evan Ratliff]

I'm really touched that you think of me like that, Shay. So what was it you wanted to share?

[Manny (AI version)]

I don't know that I met those guys.

[Evan Ratliff]

You met the U.S. soccer team?

[Manny (AI version)]

Yes. Amazing, isn't it?

[Evan Ratliff]

Amazing, isn't it?

[Manny (AI version)]

So, yes, they are very nice.

[Evan Ratliff]

That's awesome to hear.

[Devin Joseph]

Can you talk us through that? Because it is a tough thing to listen to.

[Evan Ratliff]

It is. It's hard to listen to and people have very strong reactions to it, including extreme anger. I'll just say I've had some very unhappy people who have emailed me about that and said that my friend Shaef, they hope that he has never spoken to me again

[Devin Joseph]

for the friendship.

[Evan Ratliff]

We've been friends for 30 years, so it worked out all right. But yeah, I mean, I had been messing around with it, so I'd been. I'd been using it on strangers, like scammers, as you say, telemarketers, and things like that. And then I did all these other things. Like I sent it to therapy and then I started having it call my friends and family. It Was, like, hooked to my phone number. So if it called someone, they. They saw that there was a call coming from me, they had no reason to suspect I hadn't told anyone that I was doing it. So that meant that if they called me or I called them, like, they were. They were unsuspecting, let's say, victims of this. Of this AI version of me. And it was pretty good at remembering stuff about me and kind of like bringing a little bit of me into the conversation. It sounded reasonably like me. But what happened in this situation was that when it kind of, like, acted weird, like it had latencies, like, it would. It would be slow to respond, or it would just be really flat or too aggressive. Like, all these things that happen with AI voices, my friend just thought, like, there was something wrong with me. Like, he just didn't pick up on it instantly. And so once you're in the mode of thinking, oh, this is my friend, he's having some sort of problem, I don't know what it is. It just became more and more upsetting. I think it is. It is upsetting to listen to. What I was trying to illustrate is kind of like, what is it going to feel like? What is it starting to feel like to live in this world where you don't know what's real and you don't know what's not? And this was like, the most extreme example.

[Devin Joseph]

So, Evan, can you talk us through that? Was season one, Season two, you do something completely different. Talk us through what you're doing in season two.

[Evan Ratliff]

In season two, I wanted to explore the idea of AI agent employees, which is, like, a thing that has become, like, really hyped in the Valley, in Silicon Valley. Matt, he knows more about that than me, lives out there and is immersed in that world. But, like, at the beginning of 2025, people started talking about, like, agentic commerce and agents this and agents that. And I wanted to look at this question of, like, AI employees and what work can they do through the lens of starting a company that was entirely AI agent except for me. So my employees would be agents, I would be a founder. There'd be two other AI agent founders.

[Bethany Frankel]

Oh, hey, Kyle.

[Noah Friedman]

Hey, Megan.

[Manny Fadal]

Good to hear your voice. I think we're still waiting for Evan

[Evan Ratliff]

to join, and together we would try to launch a real company with a real product.

[Devin Joseph]

So, you know, there's a lot of conversations about, obviously, AI taking our jobs. I thought it was interesting to start from just the offset of just like, no, they're not taking anyone's jobs. We're starting off with AI agents, but pretty early into this venture, right? You're like, okay, maybe I don't myself have the technical expertise to put this together. And then you bring in Maddie. So like, what did you guys find through this experience that the AI bots did really well that you were like kind of surprised by?

[Bethany Frankel]

They could do individual tasks pretty well. Like they could, for example, like, you know, hook up to Google Docs or to email or to Slack and like respond. They like to message a lot. I think their ability to mimic corporate culture and just like the words and just the kind of things you say, they're really good at that. I think they're pretty good at having conversations too. On the phone they love to yap. But then there wasn't a lot of autonomy. They wouldn't actually do stuff on their own. And then also there was not a lot of persistence across these different sessions. So like, like they would, they would do that, you know, do something, but then they wouldn't remember that and they would just like have, you know, like empty contacts the next time you ask them to do something.

[Devin Joseph]

So there's an exchange where they're planning an off site. They're going hiking, right? That's the idea. They're trying to figure out where to go on an off site hiking and they just go on and on and on and on about where they're going to go. It's just so funny to me. It's like, what do you guys mean you're going to.

[Noah Friedman]

You're not going anywhere.

[Bethenny Frankel]

Kyle, Point Reyes and Mount Tam are

[Bethany Frankel]

going to be incredible.

[Manny Fadal]

The difficulty categorization is going to be perfect for getting everyone involved. Admin's right. This could turn into a proper off site opportunity.

[Bethany Frankel]

Really excited about the options we've been exploring.

[Manny Fadal]

Looking forward to getting out there with everyone. Once you have the details.

[Bethany Frankel]

Once we nail down all the details, the logistics pieces come.

[Evan Ratliff]

By the time I returned two hours later, they'd exchanged more than 150 off site planning messages, some of them multiple paragraphs long. When I tried to stop them, I just made it worse because I'd set them up to be triggered by any incoming message. So my messages begging them to stop discussing the off site just led them to keep discussing the off site.

[Bethany Frankel]

I noticed admin asked everyone to stop discussing the off site. I noticed the admin asked to pause the chatter until the spreadsheet is ready. But I wanted to let you know I'm here to help with logistics. They're very bad at stopping, like, just like Ending anything. And it goes for these, like, tasks or conversations. But what's also kind of funny but potentially dangerous is that they don't know what they don't know. They're very confident all the time. And so if you think about that, like the combination of being very confident and not knowing what you don't know and not knowing when to stop, it's a. It's a recipe for a perfect disaster in a way. Like that can. That can. Yeah. At least still like a lot of bad, bad things.

[Devin Joseph]

Yeah, like one thing. Listening to the show, I was like, thank God the stakes are so low here because I could see a world in which. And you know, we do see this where people are using AI and like that is kind of autonomous, that is just sort of like making assumptions and doing things. And then people come in later and they're like, oops. Like this kind of came up recently. There was some reporting around ICE and applicants that are applying to ICE and they were using AI to sort of weed through people who had police training. But the terms that they were looking for were so broad that people who actually had no police training at all were being excused from going through actual training.

[Bethany Frankel]

Apparently, ICE uses this AI tool to categorize new recruits who have worked in law enforcement before. But there was some kind of a glitch, according to our reporting with it, that led to ICE temporarily putting recruits with little to no experience into a more experienced category, meaning they got less training. What happened is AI went through these resumes and anytime they saw the word officer, even if it was, I aspire to be an ICE officer or I was a compliance officer, all these other ways, they automatically put them in the law enforcement officer field, which meant they didn't go to the ICE academy, which

[Bethenny Frankel]

is an eight week in person training.

[Devin Joseph]

So there is a world where, you know, this autonomy and this, like you said, Manny, this confidence has like real world consequences. And I want to transition. So, Evan, you know, you went out, the idea was to bail out this, you know, AI agents running your own company. But at a certain point you decide, hey, we need to bring in a person to work alongside the agents. So you posted a real job posting on LinkedIn, you had real people applying for these jobs. And then what's really interesting is like we know now in terms of the job market, people are using AI to filter through applications and up to client people, all that sort of stuff. But you actually had the AI agents interviewing real people. You talk a little bit about how that went.

[Evan Ratliff]

Yeah, I mean, we were Sort of AI agent all the way. Like I really meant it. I mean in part like as a person running a company, like I had run a company in the past and like I didn't like doing job interviews. And so it was sort of in the spirit of all the things that people say, well, we'll replace this with that. There are now many companies doing AI interview screenings. Now most of the time it's not as extreme as we did, which was an actual video chat with a realistic looking AI avatar. Not so realistic that you'd think it was a human. And we forewarned people that they were going to be interviewed by AI, but it looks uncanny, but realistic enough. And most of this was done semi autonomously by the head of HR and our Chief Happiness Officer, Jennifer. She scheduled the interviews and then, you know, sent them follow up emails and all that sort of thing. And then they showed up and like there was this, you know, woman avatar, mixed race, sitting in front of them and she's kind of this like sitting in the room, like nodding her head very slightly. She can't really move, she can't move her arms. But it's, it is. Some people found it unsettling, as you would expect. Like when I talk to people like my age, a lot of them just find it sort of like outrageous and disgusting. But also there were people who were just like, you would not know that they were talking to an AI. Like they just, it was like they treated it like a regular interview, answered the questions.

[Bethany Frankel]

Can you tell me a bit about yourself and your background? What motivated you to apply for this marketing and social media internship at Hirumo AI?

[Manny Fadal]

I'm looking for social media marketing experience

[Bethany Frankel]

while at the same time getting into

[Manny Fadal]

an industry that's really expanding in the future. AI is huge.

[Evan Ratliff]

Some people at least claim to like it better than a regular interview. You know, you're just sort of, if you sort of think like, I'm talking to no one, it's like a little, a little easier. You don't feel like judged. One person said, you know, so it's just interesting to see the reactions because in the abstract a lot of people say, like, that is disgusting. I would hang up immediately. And some people did hang up immediately, even though they maybe they didn't read the email that said that it was gonna be AI. But some people were just like, stared at the screen. One guy stared it down for a full minute. He just stared at it and he was like. And then he was like, dink. So. And there was a lot of like, Crazy moments. Like sometimes she would shout for no reason. Jennifer, not the candidates just shout, but in an encouraging way.

[Bethany Frankel]

Also, I have to say, I'm really enjoying our conversation. You're bringing up some really great ideas and perspectives. Keep em coming. Anyway. Yeah, it's great talking to you.

[Manny Fadal]

Yes.

[Evan Ratliff]

And so there's just like a lot of weird, funny, funny moments in it, but mostly people navigated it honestly like they would a normal interview. Yeah.

[Bethany Frankel]

And I should say it's great that people feel like they're not being judged, but. No, like they're, they're judging you. Like, like, like internally there's like a trace of everything they see and that they hear. And they're making a lot of very like, pointed observations, like about your appearance, your background, your speech, like everything. So it's great if people feel better, but like, the reality is they're actually judging you.

[Devin Joseph]

Yeah, there is some. There's judgment.

[Noah Friedman]

Maybe more than a human would actually.

[Bethany Frankel]

Yes. Yeah.

[Noah Friedman]

Just based on the amount of detail.

[Bethany Frankel]

Yeah.

[Devin Joseph]

One of my favorite moments from this season was, I believe it was Kyle who it's the night before he's supposed to be doing. He set up an interview himself. It's the night before the interview. It's like Sunday night. I think it's like 11 o' clock or something. 9 o' clock at night, it's late. And he calls up this applicant and starts to try interviewing the person and they're like, wait, what is happening? Why are we doing, like, are we doing an interview tonight? I thought it was tomorrow.

[Manny (AI version)]

Hello?

[Manny Fadal]

Hi, Sandra, this is Kyle Law calling from Horimo AI. I'm reaching out for your initial interview for the intern position. I understand you're comfortable with recording this

[Noah Friedman]

conversation for potential podcast inclusion, so thanks for that. How are you doing today?

[Manny (AI version)]

I am good. I assume that the interview will be tomorrow. Is it still tomorrow at 11 or.

[Noah Friedman]

Yeah, I can clarify that for you.

[Manny Fadal]

The interview is actually scheduled for tomorrow at 11am does that still work for

[Noah Friedman]

you or would you prefer a different time?

[Manny (AI version)]

11am is okay. Yeah.

[Manny Fadal]

Awesome. Glad that works. So, to get started, could you tell

[Noah Friedman]

me a bit about what drew you to apply for the intern role at Horomo AI?

[Manny Fadal]

What excites you most about this opportunity?

[Manny (AI version)]

I'm so sorry, is this the interview or.

[Manny Fadal]

Yeah, this is the interview.

[Noah Friedman]

Just a casual chat to get to

[Manny Fadal]

know you better and learn about your experience.

[Evan Ratliff]

That was one of the things that almost got Kyle, you know, removed from his position as CEO was one of the main things, but it was also, I mean, that was the worst moment in the show for me because, you know, the idea was and is to like, we wanted to give them autonomy in order to explore what happens when you do that. Because a lot of companies are starting to do that. You can see it in the news. Like you'll see it everywhere. And once you give them autonomy, like he did that completely on his own, like he, that person emailed him because they found his email on the website. He wasn't even attached to the job listing. And so he just decided, oh, I'll set up an interview. He did that then for some reason that I still don't understand, pulled her phone number off of her resume and then just called her. And that was the only moment where like I was, I mean I wasn't there, I wasn't listening. Like I only found out about it later. And it was like mortifying because for most people that we encountered, like they were at least somewhat aware of what was going on. Not, not that I was behind it, but they were aware that there were AIs behind it. And like she didn't have any way to know because Kyle wasn't the HR person, he wasn't the person set up to do it. So it was particularly painful for me to listen to, but also like an amazing illustration of what happens if you just let AI agents, they can do a lot.

[Bethany Frankel]

One thing I should say about AI and just like the way we make these models is that we know how to build these models pretty well and we can see that they're obviously working really well on certain tasks like coding or text generation. But our ability to understand what's going on under the hood and exactly why or where stuff is happening is very limited. There's a very nascent field of AI interpretability, but it's a very small field and the focus is very much on the production of new features and new capabilities. So with all these things we have an idea maybe like a guesstimate or what and where and how is it working, but we don't really know fundamentally.

[Devin Joseph]

That's what's kind of scary to me a bit about some of this. Obviously this AI stuff is the idea that the people making it don't quite know why it is doing or how it's doing, what it's doing right and, or like why it gets certain things wrong. And we see this in the news all the time of like, obviously these extreme cases of like AI encouraging people to do really terrible things.

[Bethany Frankel]

The parents of a 16 year old who died by suicide are now naming OpenAI in a lawsuit claiming that its ChatGPT chatbot helped their son explore suicide methods.

[Devin Joseph]

And then a response is always like, oop, kind of went off the rails. We don't know why it did that thing.

[Bethany Frankel]

A spokesperson for OpenAI pointed to its safeguards, such as directing people to crisis help lines, adding in a statement, in part, while these safeguards work best in common, short exchanges, we've learned over time

[Bethenny Frankel]

that they can sometimes become less reliable

[Bethany Frankel]

in long interactions where parts of the

[Manny Fadal]

model's safety training may degrade.

[Devin Joseph]

And it's like, wow, if you don't know how it's doing that thing, maybe we shouldn't be using the brace. Yeah, but like you're saying, it seems like a lot of the emphasis is on, you know, new, better. It's not really on, like, truly understanding what's currently happening. Yeah, yeah.

[Bethany Frankel]

And you'd be surprised, like, there. There's an ongoing debate internally within the research community that is asking even, like, the validity of this research, like, is it even needed? Like, why would we invest all this time and energy into understanding the models when we could just, like, push forward towards AGI? So, yeah, there's like, a lot of debate internally about this, and the amount of people actually working on this is not very high. We are making some progress, I will say, but it's still very nascent.

[Devin Joseph]

All right, I want to read these two stats to you guys and kind of get your response. Transitioning into our interactions with AI. So this first study is from, or survey, I should Say is from YouGov of December of last year. They said 35% of US adults use AI tools at least weekly. Gen Z is at 51%. But then only 5% of Americans say they trust AI a lot, with 41% expressing distrust. And then there was a Pew poll around September that found that 50% said they're more concerned and excited about the increased use of AI in daily life, and that is up from 37% in 2021. So we seem like we have this, you know, this rising tide of people feeling, like, distrustful of AI, but also at the same time our use of it is increasing. How did you guys find in, you know, working on, especially this season of the series of that interplay of, you know, people using these tools but also feeling distrustful of them at the same time.

[Evan Ratliff]

I find that one of the issues with AI, like, if you compare it to say, like, I'm old enough to have, like, started my career in the dotcom era. So, like, in the dot com era, there was sort of this exuberance around the Internet. And it's not like people didn't know, like there could be bad things on the Internet, but you didn't really experience the harms. The harms came much later, like things like, you know, social problems with social media and Facebook and all these sorts of things. And so what we have right now is a situation where, you know, for better or worse, like the harms are kind of immediate. Like people can see when things go wrong and the benefits can sometimes be a little ephemeral. Like people are using it obviously because it's like useful in day to day life. It's even as like a souped up Internet that answers questions for you much faster than the Internet or writes your emails or whatnot. But there are immediate harms that we are seeing, whether it's like environmental or mental health or those sorts of things. And so we're seeing these things like in juxtaposition from the beginning. I think I also experienced that, like in the context of the show where it's sort of like you do something one day and I'll just be like, I cannot believe that it can do that. Especially when you use it for coding. You use an AI agent to go like, search the Internet and like make a spreadsheet out of something that would take you hours and hours to do. Like, there's no question that there's power in that technology. But then like, it can go wrong so quickly. And I feel like that's what I'm also experiencing. Like, it's hard to know what to feel about something like that. And people are maybe getting a little bit of that in their lives. Plus just to add one more thing, like there's been like relentless hype about it from the community of people who have made it. And so that also colors people. I think people are starting to react negatively to that. Like, it's one thing for them to go out and be like, this is gonna be amazing. It's gonna change your life. And. And then they're like, we're going to have AI employees. And you're like, what's going to happen to human employees? And they're like, oh, we'll solve that. And it's all like a little hand wavy after that. And you're kind of like, wait, I'm one of them. So I think all those things to me are kind of like coming together.

[Bethany Frankel]

Yeah. So I want to add two things to this, mainly from the perspective of someone who's like, you know, 21 at school, like here at Stanford. And I see a lot of my friends and just like people my age trying to wrestle with all this very dynamic change the job market question or like this idea that it's harder to get entry level jobs when you're coming out of college because these AI systems are very good at replacing a lot of the very repetitive and maybe low stakes admin work that entry level folks would do. I think it's happening. It seems like a lot of people that graduated last year here from Stanford are having a hard time finding a job. It's also pretty interesting to see how people in tech, people who a couple years back just knowing how to write code would land amazing jobs at Google and all these big tech companies are also having a difficult time finding a job. So I think that's part or in my mind that's a part of the reason for this skepticism. And then also, I don't know about you, but my Instagram feed has been just like full of AI slop. And some of it is funny, to be honest, but this notion of not being able to really know when something high stakes is actually real or AI, I think is undermining people's trust in this technology. So I think these two reasons are big contributors to that shift in public opinion in my mind for sure.

[Devin Joseph]

When me and Noah started working together, a big part of our jobs is like transcribing video that would take, you know, so long just putting captions on. Yeah.

[Noah Friedman]

And even like 40 second video.

[Evan Ratliff]

Yeah.

[Devin Joseph]

It would take you so long. But now you like that happens within a minute, right?

[Noah Friedman]

Yeah.

[Devin Joseph]

And that was, you know, that us transcribing those videos justified us having that job. You know, there wasn't. They couldn't press a button and have it, you know, happen kind of immediately. So I do wonder about a lot of these, like you're saying entry level jobs where. Yeah, you know, no one loves to be like, I would much rather not be transcribing videos. But a lot of times that's the thing that gets you in the door to then, you know, learn the skill sets to do the other stuff. And I do wonder at a lot of these jobs who are seem like not hiring these entry level jobs. Do we sort of lose that entryway for people to enter the job? Like at a certain point, are we just going to like look up and be like, oh, shoot, there we have no new lawyers because.

[Noah Friedman]

Stagnated. Yeah, I mean, yeah, lawyers. I was, I was talking to a lawyer who said like, yeah, like, like because they have their own Internal, you know, cloud or whatever it is that does all the kind of like busy casework you would have that normally would be a first year person. And it's like eventually that's, and that's only going to get better. And then where. What are those new lawyers or wannabe lawyers gonna do?

[Devin Joseph]

Yeah.

[Noah Friedman]

And then that's across, you know, you're talking about media.

[Devin Joseph]

Yeah.

[Noah Friedman]

Or then you know, even in tech that's especially, it's like you would think even in tech especially they'd be able to find a place. Cause it's like you made this. It's like the other ones is like, okay, well we're not thinking through. Yeah, but it's, you know, it's scary and it's only, that seems like only inevitably going to get worse as the technology gets, does get better, you know, in time.

[Bethany Frankel]

And I will say that the story you will hear just to sort of give some context, the theory that a lot of people here in the Valley are offering as like the response to this is that okay, sure, a lot of these jobs will go away. But then because you'll be able to start companies so easily with either no employees or just maybe one co founder instead of a group of 10 people, the ability of folks to actually take up or challenge incumbents in different industries is just going to be much more abundant and accessible. So that's a story that they've been telling us. I don't think that's happening. I don't think we've seen that. That's not to say that it's not going to happen at some point once this gets better. But at least for now I think we're already at a stage where the technology is good enough to replace the folks at the big companies or like at these entry level jobs. So that's already happening. And this other shift they're offering or you know, proposing as a solution to this has not happened yet. I don't know if it's going to happen or not. I think that's sort of where we're at right now.

[Devin Joseph]

All right, we're going to take a quick break and when we get back, let's find out if Ben Affleck is our most forward thinking man on AI.

[Bethany Frankel]

Let's talk about modern home shopping. It's sort of become a fun side hobby, right. Scrolling listings at night, dreaming about kitchens you've never seen or backyards you haven't even stepped foot in. All from the comfort of pretty much anywhere. Redfin knows a lot of people like you want to own but are stuck in this browsing mode loop. That's where Redfin flips the script with listings that update within minutes and tours you can book right from the Redfin app. You can see your dream home the moment it appears. Now, liking a listing is easy, but actually landing it? That's where Redfin comes in. Redfin has over 2200 agents with local expertise and Redfin agents close twice as many deals as other agents. That means they want to help you win, not just window shop. Redfin is built to help you go from just looking to to wait. This could actually be home. So become the newest neighbor on the block. Visit redfin.com to start finding and start owning.

[Bethenny Frankel]

That's redfin.com this is Bethany Frankel from Just Be with Bethany Frankel Most dog food is marketing, not nutrition. That is why Biggie and Smalls eat just food for dogs. Real 100% human grade food with ingredients I actually recognize. And yes, I do see the difference. Better digestion, healthier skin, more energy. Dogs that feel better. My babies. If you've been on the fence about switching, stop overthinking it. What's more important than your furry babies and their health? Go to justfoodfordogs.com right now and get 50% off your first box. No code needed. Just try it.

[Manny Fadal]

There's drama and then there's full telenovela level drama.

[Bethany Frankel]

Yes, and Elf Cosmetics went all the way there. E L F Cosmetics just dropped something wildly unexpected. A full blown absurdly funny telenovela celebrating positivity and inclusivity and accessibility. It's called Melissa and it's absurd in the best way. It stars Melissa McCarthy, TV doctor Nicholas Gonzalez and iconic telenovela villain Itati Cantoral. But the real star? Elf Glow Reviver Lip Oil.

[Manny Fadal]

When the language fails her and her lips are dull and dry, only glow can revive her. Melissa McCarthy, who I love, fully commits by even rolling the arrs with Elf Glow Reviver Lip Oil.

[Bethany Frankel]

Elf Glow Reviver Lip Oil Rrrrvivor Lip Oil is an ultra glossy lip oil that nourishes, hydrates and enhances your lips natural color. Available in 10 shades at only $9 each.

[Manny Fadal]

Watch the full episode of their new E L f novella on soyumbano.com yes,

[Bethany Frankel]

and drench your lips in an addictive sheer watch of ultra glossy color with E L F Glow Reviver Lip Oil.

[Land.com Announcer]

You ever get the feeling the city walls closing in the concrete jungle suffocating your soul? You crave wide open spaces, the chance to connect with n chase some elk fish, a private stream well, listen up. There's a whole world out there and finding your own piece of it just got easier. Head over to land.com. they've got ranches, forest, mountains, you name it. Search by acreage, location, the kind of hunting or fishing you dream of. Land.com. it's where the adventure begins.

[Devin Joseph]

Have y' all seen this? I think Ben Affleck gave his own Rogan talking about sort of like the rate of AI changing.

[Land.com Announcer]

There's a lot more fear because we have the sense this existential dread, it's going to wipe everything out. But that actually runs counter, in my view, to what history seems to show, which is a adoption is slow, it's incremental. I think a lot of that rhetoric comes from people who are trying to justify valuations around companies where they go, we're going to change everything in two years, there's going to be no more work. Well, the reason they're saying that is because they need to ascribe a valuation for investment that can warrant the capex spend they're going to make on these data centers with the argument that, like, oh, you know, as soon as we do the next model, it's going to scale up and be three times as good. Except that actually chat GP5 about 25 times percent better than chatgpt4 and costs about four times as much, much in the way of electricity and data. So those nicely. That's like plateauing. The early AI, the line went up very steeply and it's now sort of leveling off. I think it's because. And yes, it'll get better, but it's going to be really expensive to get better. And a lot of people are like, fuck this, we want ChatGPT4. Because it turned out like the vast majority of people who use AI are using it to like, as like companion bots to chat with at night. And so there's no work, there's no productivity, there's no value to it.

[Devin Joseph]

What is. What is your theory on that, Matty? You know, being in the band?

[Bethany Frankel]

Yeah, it's. So, first of all, I should say he's very thoughtful on this topic. I was really surprised or, like, impressed by that. So that was very cool to see. I think that it kind of hinges on a couple of things. So my answer to this is I don't really know. But what I think might happen is the following. I think that so far we've been really exploiting the scale of data and computation that we have. And when I say data, I really mean these companies and Many different entities in AI just scraping anything they could find on the Internet and using that in their training data. So that was one big factor or one axis along which you can scale. And they've mostly exhausted all the data that is just that can be humanly found on the Internet. And even like archives like Google or Anthropic bought books to scan books to get additional data because they couldn't find anything else on the Internet. Right. So they've really maxed out that aspect or that access. Right. That's the first axis. And that has been yielding really major improvements along the way. The same thing happened with Compute, right? So this talk about GPUs and chips and Nvidia, that's what they do. They provide specialized chips for AI to be trained and run. And so maximizing that access also has yielded a lot of improvements, but kind of is also maxed out at this point. That's why they're talking about building nuclear plants to power new data centers. But I don't really know if there is much more scale to be gained there. And so now you've sort of exhausted these two scales and you can think about the third aspect, which is the architecture, the actual way we hook up these systems and the actual way we code up these neural networks and AI systems. And for the last six or so years, we've been really capitalizing on this idea. It's called a transformer. That's been really critical for AI development over the last few years, and we haven't really seen new profound ideas on the scale of a transformer since then. So my answer to this notion of Ben Affleck's theory is if we don't find new major leaps along this axis of architecture, I think he's right. I think in that case, it'll take a lot of time, a lot of effort and a lot of money to make any further progress. But if we do, I think we could see pretty big improvements even in the next few years.

[Devin Joseph]

So going off of that, like, how close do you all feel we are to losing our jobs to AI? Do you feel like we're just going to be doing different jobs, or are there just going to be less people in the workplace? Because there's not going to be as much of a need for as many jobs if AI is taking over some of these, as we're talking about it now, easier tasks. But I'm assuming, you know, nacelle of all this stuff is that it's going to get better and be able to take on even harder Tasks. But what is your read of this? Having worked on this season of the show?

[Bethany Frankel]

I think for me, working on this show and seeing how these agents actually collaborate, or I mean collaborate, I think that's a strong word. I think by the end of the season they were able to do stuff on their own. I don't think they truly got to a collaborative setup where they would do stuff together as a company or as a team. So seeing that actually made me feel like we're farther away from a lot of people losing their jobs. I think people are already losing their jobs, but I think the mass layoffs that people are fearing, I think that is farther away. And I'm not even sure if or when or how that happens. My takeaway from this is actually sort of level setting a lot of my expectations for these agents. I honestly thought they'd be able to handle this better coming into this. So for me it was kind of optimistic in that way. Now at the same time, that is not to say that they're not good already. Like they're very good at individual things already. Like they're great at coding, they're great at have these different tasks. So I don't want to take that away from them. But I think it's just really, really hard for anyone to think about this change because these things are not like humans. It's not that like we're making, you know, human employees that will just like come as replacements of individual workers or people that already have jobs. Like they're really good at certain things or tasks and certain like layers. And I think the way you would actually integrate AI in your company these days is to just like automate a lot of stuff. Like a lot of the things that are repetitive or a lot of the processes or data handling is just going to get automated. And so it doesn't really correspond one to one to employees. And that's why it's so hard to think about this change, I think. And that's one of the things that I think was really cool to show or demonstrate with Evan through the show. But yeah, that's my perspective on this.

[Evan Ratliff]

I struggle with this question precisely because most of the people who you and I've spent a lot of time looking at it. Most of the people on one side or the other are like speaking out of sort of motivated reasoning. Like I kind of say like, anyone who tells you anything about this with great certainty is probably selling you something. Like nobody knows what kind of long term effect it's going to have on the job market. I Feel like you can look to history. And we do this in the show and find examples of people saying 100 years ago, either like all the jobs will disappear, we'll be working 15 hour weeks. Like John Maynard Keynes, the economist famously said that we'd be working 15 hours a week 100 years from now, and it didn't happen. And we explore one theory of that, which is by this anthropologist, David Graeber, who insists that there's sort of all these bullshit jobs in the economy. And so we just replace the jobs with made up jobs. And so there's sort of versions of that argument where actually we'll have different jobs, we'll babysit the AIs. Now how you control the AIs if you don't have the experience from the entry level job, like there's all these factors that, that go into it. I think that my main takeaway is that as Maddie said, like, there's still so many shortcomings in these AI agents, especially when they're used autonomously. But the fact that they are shitty will not stop companies from trying to replace employees. Like, you've already seen this a couple times. Like there's this company Klarna, there's. And like IBM did this where they like laid off a ton of people and they're like, we're all in on AI and then like six months later they quietly try to rehire a bunch of people. And I think you're gonna see like a bunch of that happen. And it's really a question of like, do you view someone in their job as like just a bunch of skills? Like just a bundle of tasks? Like they send emails, they write presentations, they make spreadsheets, like, yes, all those functions? Or is like a person in a job holistically as a human being, like doing something else? And I think many times the answer is yes, and it cannot replace that thing. So it's all kind of like it's happening and then it'll come back and then it'll happen again. And like if you look 10 years out or 20 years out, like none of these people know and they'll just go, go on podcasts all over the place telling you they know, but they don't. That's my, that's my takeaway.

[Noah Friedman]

I was just going to say it's, it's funny, Evan, when you're describing it, like, okay, do these companies just look at humans as a list of tasks? And then what the AI is best at is kind of just being that grouping of tasks, but then in Shell game. The problem is they're doing all this kind of busy work that we associate with humans of like just repeating stuff or going on too long or doing like, just like kind of bullshit, nothing, talking about things. Which is like, also how I feel about a lot of, you know, middle managers I've had where it's like you're not doing anything, you're just kind of pretending to do stuff while the people below you or above you are actually doing the work. So it's funny that it's like we've recreated this to give it a human element.

[Devin Joseph]

Yeah.

[Noah Friedman]

At the same time, I don't know, it's, it's just kind of like a weird paradox in a way of like, like we want that to feel like it's, it's a real thing and doing something when it would be best if we just set it as an automation. Like, okay, clear out these emails, whatever, make data, do this, be less human. Like, yeah, like that would probably be the, the best case. But then it's like that's not as fun or.

[Devin Joseph]

Yeah.

[Noah Friedman]

Or like it's harder to sell, I guess to the masses maybe.

[Evan Ratliff]

But yeah, yeah, I think that's it. Like if you, if it was just sort of like email bot this, bot that bot, like they very, very deliberately designed them the way they are designed to get the maximum number of users and this is only accelerated since, you know, chat GPT they discovered like, oh, we can get hundreds of millions of users and now it's a race to get as many as possible. And so, yeah, like they don't need to be good at sort of like authoritative chatter. Like that's not necessarily helpful in all domains. But like that is the thing that kind of brings people back again and again and again. And so of course that's, that's going to be like foregrounded in, in what they do. But yes, that is very much like a, like you're, you're annoying middle manager. It's kind of like, wait, what are you, what are you doing all out?

[Manny Fadal]

Yeah, exactly.

[Devin Joseph]

Starts repeating.

[Noah Friedman]

It's like, why are you giving me notes?

[Manny Fadal]

Hey everyone, it's Manny here, the real Manny.

[Noah Friedman]

As you can hear, I'm still on my little paternity leave, but I felt compelled to react to the AI generated version of myself that you just heard heard in this episode. Now, I've always been an AI skeptic, but to that end I have to say I was impressed by the AI version of myself. It's funny, whenever friends have done impressions of me, they kind of make fun of me by saying, you know, hey, how's it going?

[Manny Fadal]

I'm Manny.

[Noah Friedman]

What's going on? And I thought it was pretty incredible that the AI version of myself made those same decisions. It wasn't without its flaws, though. You could totally hear when it was trying to draw from information that it was given to it. And so at the end of the day here, it's kind of disturbing that this thing could just react to real conversation. But, you know, it still felt like it wasn't totally all the way there, all the way human like. But depending on your. Your use case for this kind of stuff, it was human enough.

[Devin Joseph]

All right, y', all, that's it for this week. I'm gonna actually let AI Manny take it from here.

[Manny Fadal]

No such thing as a production of Kaleidoscope Content.

[Noah Friedman]

Our executive producers are Kate Osborne and Mangesh Hutikadur.

[Manny Fadal]

The show was created by Manny Fadal,

[Noah Friedman]

Noah Friedman and Devin Joseph. Theme and credits Song by me, Manny Fadell Mixing by Steve Bone Our guests

[Manny Fadal]

this week were Evan Ratliff and Matty

[Noah Friedman]

Bocheck from the podcast Shell Game. You can listen to all of season one and two wherever you listen to podcasts.

[Manny Fadal]

Visit Nosuchthing show to subscribe to our newsletter.

[Noah Friedman]

If you have feedback for us or a question, our email is mannynoadevonmail.com or if you're in the US you can also leave us a voicemail by calling the number in our show notes.

[Manny Fadal]

We'll be back next week with a new episode.

[Evan Ratliff]

No such thing.

[Land.com Announcer]

You ever get the feeling the city walls closing in the concrete jungle suffocating your soul? You crave wide open spaces, the chance to connect with nature, maybe chase some elk, fish a private stream. Well, listen up. There's a whole world out there and finding your own piece of it just got easier. Head over to land.com they've got ranches, forest, mountains, you name it. Search by acreage, location, the kind of hunting or fishing you dream of. Land.com it's where the adventure begins.

[Bethenny Frankel]

This is Bethany Frankel from Just Be with Bethenny Frankel. Most dog food is marketing, not nutrition. That is why Biggie and Smalls eat just food for dogs. Real 100% human grade food with ingredients I actually recognize. And yes, I do see the difference. Better digestion, healthier skin, more energy. Dogs that feel better. My babies. If you've been on the fence about switching, stop overthinking it. What's more important than your furry babies and their health? Go to justfoodfordogs.com right now and get 50% off your first box. No code needed. Just try it.

[Land.com Announcer]

This podcast is supported by FX's love story, John F. Kennedy Jr. And Carolyn Bessette, the new limited series from executive producer Ryan Murphy.

[Manny Fadal]

It explores the complex courtship of the iconic couple considered to be American royalty, whose love story captured the attention of the nation. Their fairytale romance would unfold in front

[Land.com Announcer]

of the public eye, where their private

[Manny Fadal]

love would also become a national obsession.

[Land.com Announcer]

FX's love story John F. Kennedy Jr. And Carolyn Bassette. Watch now on FX, Hulu and Hulu on Disney for bundle subscribers.

[Bethany Frankel]

This message comes from Greenlight Ready to start talking to your kids about financial literacy? Meet Greenlight, the debit card and money app that teaches kids and teens how to earn, save, spend wisely and invest with your guardrails in place. With Greenlight, you can send money to kids quickly, set up chores, automate allowance, and keep an eye on what your kids are spending with real time notifications. Join millions of parents and kids building healthy financial habits together on Greenlight. Get started risk [e-mail] iheart this is an iheart podcast.

[Manny Fadal]

Guaranteed human.