Will AI take our jobs?

Summary

---

NO SUCH THING – "Will AI Take Our Jobs?"

Podcast: NO SUCH THING
Host: Kaleidoscope (Devin Joseph, Noah Friedman, and AI Manny)
Guest Experts: Evan Ratliff & Matty Belichick (from "Shell Game" Podcast)
Date: February 18, 2026

---

Episode Overview

This episode dives into the timely and contentious question: Is AI really coming for our jobs? Using their signature blend of personal banter, investigative research, and expert interviews, hosts Devin and Noah explore how close artificial intelligence truly is to replacing humans in the workforce. They experiment with an AI-generated co-host (AI Manny), test out cutting-edge AI tools, and interview journalists Evan Ratliff and tech advisor Matty Belichick, who built and ran a company staffed almost entirely by AI agents. The show balances humor, skepticism, and genuine inquiry into AI’s capabilities, pitfalls, and social impact.

---

Key Discussion Points & Insights

1. Introducing AI Manny and the "AI as Employee" Experiment

• [02:37]–[06:54]: The episode opens with the hosts phoning "Manny"—but it's actually an AI-generated voice and personality, showcasing current AI capabilities in mimicking real people.

  • Experiment Purpose: To see how convincingly AI can impersonate a real personality, and to highlight the implications for media and employment.
  • Reactions: Hosts discuss pros/cons—good for basic conversation, but off in tone and a little rambly.
  • Quote (Devin): "The voice was a little off...like, the issue is just rambling." [07:31]
  • Quote (Noah): "Manny's a little better at social cues, thankfully. The real Manny." [07:42]

• [10:32]–[12:01]: Guest Evan Ratliff explains how easily AI "Manny" was created.

  • It took just 15–20 minutes using a consumer tool (11 Labs) and some show audio.
  • AI prompts included personality info generated by ChatGPT.
  • Quote (Evan): "You could do it in 15 minutes. That’s kind of scary." [12:01]

---

2. AI on the Job: The "Shell Game" Podcast Project

• [12:16]–[16:13]: Evan Ratliff recounts his experiment in using an AI agent to replace himself, both for mundane interactions (like dealing with scammers) and personal calls.

  • Notable Experiment: AI Evan calls a friend, resulting in a cold, off-putting conversation that unsettled listeners and raised ethical concerns.
  • Quote (Evan): "What is it going to feel like to live in this world where you don't know what's real... this was the most extreme example." [15:39]

• [16:13]–[18:23]: Season two: Building a business run by AI agents.

  • Objective: Launch and operate a company with only AI as employees (except for Evan).

• AI Capabilities vs. Limitations ([17:39]–[18:23])

  • Can handle individual, repetitive tasks well (emails, Google Docs, Slack).
  • Major Flaws: Lack autonomy, can't persist memories across sessions, struggle to actually "do" things independently, and often mimic corporate culture to a laughable extent.
  • Quote (Matty): "Their ability to mimic corporate culture... they're really good at that." [17:43]

---

3. Real-world Examples: AI Run Amok

• [18:23]–[20:00]: Hilarious out-of-control off-site planning by AIs—over 150 messages exchanged about a fictional hike.

  • Agents can't stop talking and confidently make mistakes.
  • Quote (Matty): "They're very bad at stopping, at ending anything... And they're very confident all the time." [19:34]

• [20:42]–[21:18]: Real consequences of AI confidence and lack of nuance.

  • Example: ICE used AI to parse resumes; tool misinterpreted "officer" in any context, causing underqualified recruits to be misclassified and miss key training.
  • Takeaway: AI’s “confidence” amplifies bureaucratic errors with serious effects.

---

4. AIs Interviewing Humans for Real Jobs

• [22:07]–[25:06]: Evan describes letting their AI agents conduct video interviews with real job applicants.

  • Some candidates preferred the AI (felt less judged), while others found it "unsettling" or hung up immediately.
  • Quote (Evan): "We forewarned people... but some people were just like, you would not know that they were talking to an AI." [23:29]
  • Matty adds: "No, like, they're judging you. Like, internally there's like a trace of everything... they're making a lot of pointed observations." [25:06]

• [25:37]–[27:07]: Classic incident: AI CEO (Kyle) contacts a candidate late at night, confusing and distressing them—a real-life illustration of the risks of AI autonomy.

  • Quote (Evan): “He did that completely on his own…mortifying, but also an amazing illustration.” [27:07]

---

5. Limits of AI: We Still Don’t Know Why It Does What It Does

• [28:26]–[30:15]: AI interpretability is minimal; even the builders don’t always understand model "reasoning."
  • Few researchers focus on interpretability versus chasing new features/capabilities.
  • Quote (Matty): "We have an idea, maybe like a guesstimate of what and where and how it’s working, but we don’t really know fundamentally." [29:02]

---

6. Public opinion: Rising Use, Rising Distrust

• [30:45]–[35:33]: Survey statistics: Use is surging (35% of adults weekly, 51% Gen Z), but only 5% fully trust AI. Concern is rising faster than excitement.

  • Quote (Evan): "The harms are kind of immediate—people can see when things go wrong, and the benefits can sometimes be a little ephemeral." [31:59]
  • Quote (Matty): "This notion of not knowing when something high-stakes is actually real or AI... is undermining people’s trust." [35:08]

• Job market concerns: AI is eliminating entry-level “grunt work”—like transcription or basic legal research—that used to be a foot-in-the-door for new workers.

  • Quote (Noah): "I was talking to a lawyer who said... busy casework you would have that normally would be a first year person... that's only going to get better, and then where, what are those new lawyers gonna do?" [36:30]

---

7. Is Tech’s “Entrepreneurial Utopia” Real?

• [37:18]–[38:16]: Silicon Valley says: Automation will lower barriers to starting companies, so job destruction is balanced by entrepreneurship. But the panel is skeptical:
  • No boom in new enterprises visible yet—displacement is happening, but the “new jobs” haven’t materialized.
  • Quote (Matty): “That shift... has not happened yet. I don't know if it's going to happen or not.” [38:16]

---

8. Is Ben Affleck the Most Forward-Thinking Mind on AI?

(Lighthearted, but thoughtful digression)

• [40:13]–[43:50]: Ben Affleck’s remarks on a podcast (via Joe Rogan): AI advances are plateauing and adoption will be slow because of cost and diminishing returns.
  • Matty explains data and compute scale are nearly maxed out; massive leaps require new architectural innovations (e.g., beyond "transformers").
  • Quote (Matty): "So my answer... is if we don't find new major leaps... it'll take a lot of time, effort and money to make any further progress." [43:43]

---

9. So: Is AI Coming for All Our Jobs?

• [44:23]–[49:10]: Matty and Evan’s nuanced take:

  • We’re further than people think from mass layoffs caused directly by AI agents, but entry-level/repetitive roles are already being automated.
  • AI doesn’t directly replace entire employees—just task bundles.
  • Quote (Matty): “My takeaway... is actually sort of level-setting my expectations for these agents.” [44:23]
  • Quote (Evan): "As Matty said, 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." [46:14]

• Paradox explained: Companies view jobs as a list of tasks (which AI can mimic). But AI also replicates “human” workplace flaws (busywork, rambling, inefficiency).

  • Quote (Noah): "It’s just kind of like a weird paradox… we want that to feel like it’s a real thing... when it would be best if we just set it as automation." [49:11]

---

10. Final Thoughts from The Real Manny

• [50:33]–[52:01]: After all, the real Manny checks in to review AI Manny.
  • Impressed—but disturbed: "It was human enough... but depending on your use case, it wasn’t totally all the way there."
  • Key take: Even impressive AI clones aren’t really “real”—yet for many transactional purposes, “good enough” is achievable now.

---

Notable Quotes & Memorable Moments (with timestamps)

• AI Manny's Hot Take: "We've all collectively decided that being busy is a personality trait... nothing actually good comes from that state. Like, all the best ideas, the best conversations, the best work—it happens when you have space to think." (AI Manny, [04:44])
• The 15-Minute AI Manny Build: "You could do it in 15 minutes. That’s kind of scary." (Devin Joseph, [12:02])
• On AI's Corporate Chatter: "Their ability to mimic corporate culture... they're really good at that." (Matty Belichick, [17:39])
• AI Interviewing Humans: "We forewarned people... but some people were just like, you would not know that they were talking to an AI." (Evan Ratliff, [23:29])
• On Model Transparency: "We have an idea, maybe like a guesstimate... but we don’t really know fundamentally." (Matty Belichick, [29:02])
• On Tech’s “Job Creator” Narrative: "That shift... has not happened yet. I don't know if it's going to happen or not." (Matty Belichick, [38:16])
• Cautious Optimism: “My takeaway... is actually sort of level-setting my expectations for these agents.” (Matty Belichick, [44:23])
• On the Fundamental Uncertainty: "Anyone who tells you anything about this with great certainty is probably selling you something. Nobody knows..." (Evan Ratliff, [46:14])

---

Key Timestamps for Segment Navigation

• [02:37] Introduce AI Manny / AI impersonation experiment
• [10:32] How AI Manny was made (voice cloning)
• [12:16] Evan Ratliff’s AI “Shell Game”—deep dive
• [17:39] What AI "agents" do well and where they fail
• [22:07] AI interviews real job applicants
• [28:26] Why we can't understand AI's inner workings
• [30:45] Stats: AI use vs. trust in the US
• [36:30] How AI is reshaping entry-level and legal jobs
• [40:13] Ben Affleck on AI hype, cost, and the “plateau”
• [44:23] Experts’ takes: Will AI truly replace most jobs?
• [50:33] The real Manny on AI clones—impressed yet uneasy

---

Tone and Language

The episode’s tone is a blend of friendly banter, sharp skepticism, and open-minded inquiry. The hosts use humor and humility (“Maybe that’s just me projecting—doing less is kind of revolutionary”) to navigate serious anxieties about technological change.

---

Summary Takeaway

AI is already reshaping how entry-level, repetitive, and admin work happens—but replacing all jobs is a much bigger leap, full of technical, social, and philosophical limits. For now, the sharpest risk may be in how readily companies try (and often fail) to slot AI into roles previously occupied by humans, primarily to cut costs. And as we leap forward with little interpretability, trust in AI among the public is actually decreasing—even as adoption rises. The episode leaves listeners with plenty to think about: Is “human enough” good enough? Who will supervise these new AI coworkers? And if AI can mimic us, who do we become?

---

Transcript

[Matty Belichick]

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. Will AI take our jobs?

[Evan Ratliff]

There's no such thing. No such thing.

[Narrator/Advertiser]

Run a business and not thinking about podcasting. Think again. More Americans listen to podcasts than add supported streaming music from Spotify and Pandora. And as the number one podcaster, iHeart's twice as large as the next two combined. Learn how podcasting can help your business. Call 844-844-IHeartRadio. WSECU isn't just one of Washington's best credit unions. We're a Forbes Best in State five years running.

[Devin Joseph]

Why?

[Narrator/Advertiser]

Because we put you first. Lower fees, early paydays, financial guidance and service second to none. As a member owned cooperative, we love Washington as much as you do. From the Olympic mountains to the rolling Palouse. Join us and discover how much we care about your financial well being. Because what we really do best is invest in you. Visit wsecu.org today to learn more. Washington let's credit union.

[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.

[Narrator/Advertiser]

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 draft 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, we're 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.

[AI Manny]

Hey, this is Manny.

[Noah Friedman]

Hey, Manny.

[AI Manny]

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.

[AI Manny]

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?

[Noah Friedman]

Things. Things are great. 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?

[AI Manny]

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.

[Noah Friedman]

Not on Mike.

[Devin Joseph]

Yeah, don't really like that guy.

[AI Manny]

Ha. Oh, man, I love that energy. Nothing says we're a functional team like barely tolerating your co worker, Right? That's honestly the foundation of every great creative partnership. Just sitting, simmering resentment, and the occasional moment of begrudging respect. What did he 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]

Generally, I don't like the guy.

[Noah Friedman]

Just resentment.

[Devin Joseph]

Real quick, Manny, we want to start this episode with a hot take. Give us your latest hot take.

[AI Manny]

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 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, Manny.

[AI Manny]

Yeah, no problem.

[Evan Ratliff]

Before.

[AI Manny]

Can't promise fire every time. Before.

[Devin Joseph]

Before we let you go.

[AI Manny]

Time.

[Devin Joseph]

I know you're. You're. You're limited on time.

[AI Manny]

You.

[Devin Joseph]

You've constantly been telling us that you. You're very busy and your. 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? Noah.

[AI Manny]

Oh, man. You're really going to make me do this.

[Devin Joseph]

Yep.

[AI Manny]

All right, look, I'm gonna say this with all the love in the world. It's you. 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 there's probably over there doing, I don't know, whatever Noah does. Big Noah, dot. But yeah, you win. 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.

[AI Manny]

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.

[Noah Friedman]

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.

[Devin Joseph]

Yeah.

[Noah Friedman]

Timber. 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 pretty solid and, like, actually could have a conversation, you know.

[Devin Joseph]

Very responsive.

[Noah Friedman]

Exactly. Yeah. 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.

[Noah Friedman]

Yeah, Manny's a little better at social cues, thankfully. The real Manny.

[Devin Joseph]

That is the real Manny.

[Noah Friedman]

Yeah.

[Devin Joseph]

All right, we're going to talk to the guys. Who helped us make this right. After the break.

[Bruce Valanch]

Hello, podcast fans. It is I, Bruce valanch. For over 25 years, I worked on the Academy Awards. So you didn't have to. In that time. I've seen and heard things that should not be seen or heard or certainly felt. And now for the first time, I'm sharing all my behind the scenes stories and firsthand knowledge about the Oscars. The blood, the sweat, the tears, the slap, all the things you didn't see. So join me as I use humor and insight to break down the Oscar awards of the past to explain how and why your favorite movie didn't win, why some actors and some directors had to fire their agents, and how the whole process works or sometimes doesn't work. This is the Oscars. What were they thinking? Available wherever you get podcasts.

[Evan Ratliff]

New year, new vibe. You want the warmth of a drink, that smooth little kick. But you also want to wake up tomorrow feeling amazing. That's where RK comes in. RK is the world's first zero proof spirits brand and they invented the warm molecule, giving you the burn of whiskey or tequila without a drop of alcohol. Start the year strong with 28 bold zero proof spirits, zero calories, zero sugar, zero regrets. So you can celebrate big and still keep your resolution on track. Start the year right. Join the Zero Proof Resolution at rkbeverages.com.

[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 like voice needs. They're like the biggest AI voice player probably at this point. And then I did a. 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 ChatGPT, so it was, you know, really just fully going in on it. 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. Evan, 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?

[AI Manny]

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?

[AI Manny]

Oh, you're an AI.

[Evan Ratliff]

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

[AI Manny]

Stop repeating the same thing? It's annoying.

[Devin Joseph]

And some really creepy. In the sturming 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.

[AI Manny]

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?

[Devin Joseph]

What?

[AI Manny]

That.

[Evan Ratliff]

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

[AI Manny]

I don't know that I met those guys.

[Evan Ratliff]

You met the U.S. soccer team?

[AI Manny]

Yes. Amazing, isn't it?

[Evan Ratliff]

Amazing, isn't it?

[AI Manny]

So, yes, they are very nice.

[Evan Ratliff]

That's awesome to hear.

[Devin Joseph]

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

[Evan Ratliff]

It is. It's hard to listen to. People have very strong reactions to it, including extreme anger. I'll just say I've gotten 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 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 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 saw that there was a call coming from me, they had no reason to suspect I hadn't told anyone that. 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 be slow to respond or. 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 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, Emmett, 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, in the Valley, in Silicon Valley. Mattie, 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, 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 agents except for me. So my employees would be agents, I would be a founder, there'd be two other AI agent founders.

[Narrator/Advertiser]

Oh, hey Kyle.

[Jennifer (Chief Happiness Officer)]

Hey Megan. 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?

[Matty Belichick]

They, 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 like 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 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'd 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 gonna go. And it's just so funny to me. It's like, what do you guys mean you're going?

[Noah Friedman]

So you're not going anywhere.

[Narrator/Advertiser]

Kyle, Point Reyes and Mount Tam are going to be incredible.

[Jennifer (Chief Happiness Officer)]

The difficulty categorization is going to be perfect for getting everyone involved.

[Evan Ratliff]

Admin's right. This could turn into a proper off site opportunity.

[Narrator/Advertiser]

Really excited about the options we've been exploring.

[Matty Belichick]

Looking forward to getting out there with.

[AI Manny]

Everyone once you have the details along.

[Narrator/Advertiser]

The way with us, once we nail.

[Matty Belichick]

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.

[Matty Belichick]

I noticed Admin asked everyone to stop discussing the off site.

[Narrator/Advertiser]

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 literally logistics.

[Matty Belichick]

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, leads to 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, 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.

[Narrator/Advertiser]

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.

[Matty Belichick]

To be an ICE officer or I was a compliance officer, all these other.

[Narrator/Advertiser]

Ways, they automatically put them in the.

[Matty Belichick]

Law enforcement officer field, which meant they.

[Narrator/Advertiser]

Didn'T go to the ICE academy, which is an eight week in person training.

[Devin Joseph]

So there is a world where, you know, this autonomy and this, like you said, many, this confidence has like real world consequences and I want to transition. So Evan, you know, you went out, you, 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 we know now in terms of the job market, people are using AI to filter through applications and acceptance, 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. 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 just like sitting in the room, like nodding her head very slightly. She can't really move, she can't move her arms. But 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 it was like they treated it like a regular interview, answered the questions.

[Narrator/Advertiser]

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.

[Evan Ratliff]

I'm looking for social media marketing experience.

[Narrator/Advertiser]

While at the same time getting into.

[Devin Joseph]

An industry that's really expanding in the future.

[Evan Ratliff]

AI is huge. 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 you know, 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, 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.

[Narrator/Advertiser]

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

[Evan Ratliff]

Anyway, yeah, it's great talking to you. Yes. 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.

[Matty Belichick]

Yeah. 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.

[Matty Belichick]

Yes. Yeah.

[Noah Friedman]

Just based on the amount of detail.

[Matty Belichick]

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 the interview tonight? I thought it was tomorrow.

[AI Manny]

Hello.

[Jennifer (Chief Happiness Officer)]

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

[AI Manny]

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

[Jennifer (Chief Happiness Officer)]

Yeah, I can clarify that for you. The interview is actually scheduled for tomorrow at 11am does that still work for you, or would you prefer a different time?

[AI Manny]

11Am is okay. Yeah.

[Jennifer (Chief Happiness Officer)]

Awesome. Glad that works. So, to get started, could you tell me a bit about what drew you to apply for the intern role at Horomo? AI, what excites you most about this opportunity?

[AI Manny]

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

[Jennifer (Chief Happiness Officer)]

Yeah, this is the interview. Just a casual chat to get to 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, he did that completely on his own. 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.

[Matty Belichick]

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 virulent. Like, 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 of 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.

[Narrator/Advertiser]

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.

[Narrator/Advertiser]

A spokesperson for OpenAI pointed to its safeguards, such as directing people to crisis helplines, adding in a statement, in part. While these safeguards work best in common short exchanges, we've learned over time that they can sometimes become less reliable in long interactions where parts of the model 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.

[Matty Belichick]

Yeah, yeah. And you'd be surprised. Like, 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, is not very high. We are making some progress, I will say, but it's still very nascent.

[Devin Joseph]

All right, I'm going to read these two stats to you guys and kind of get your response transitioning into our interactions with AI. So this first study or survey says 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 dot com 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. 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 then they're like, we're going to have AI employees. You're like, what's going to happen? The 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.

[Matty Belichick]

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.

[Devin Joseph]

In my mind for sure. When me and Noah started working together, a big part of our jobs is like transcribing video, you know, so long. Yeah. 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 into 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 start to lose that entryway for people to, 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.

[Noah Friedman]

No new lawyers because stagnated. Yeah, I mean, yeah, lawyers. I was, I was talking to a lawyer who said like, yeah, 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? 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 because it's like you made this. It's like the other ones, it's 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 does get better, you know, in time.

[Matty Belichick]

Now 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 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.

[Bruce Valanch]

Hello podcast fans. It is I, Bruce valanch. For over 25 years I worked on the Academy Awards. So you didn't have to. In that time I've seen and heard things that should not be seen or heard or certainly felt. And now for the first time I'm sharing all my behind the scenes stories and first hand knowledge about the Oscars. The blood, the sweat, the tears, the slap, all the things you didn't see. So join me as I use humor and insight to break down the Oscar awards of the past to explain how and why your favorite movie didn't win, why some actors and some directors had to fire their agents, and how the whole process works or sometimes doesn't work. This is the Oscars. What were they thinking? Available wherever you get Podcasts.

[Narrator/Advertiser]

Not every sale happens at the register. Before AT&T business Wireless checking out customers on our mobile POS systems took too long. Basically a staring contest where everyone loses. It's crazy what people say during an awkward silence. Now transactions are done before the silence takes hold. That means I can focus on the task at hand and make an extra sail or two. Sometimes I do miss the bonding time.

[Matty Belichick]

Sometimes AT&T business Wireless Connecting changes everything.

[Devin Joseph]

Have y' all seen this? I think Ben Affleck, he was on Rogan talking about sort of like the rate of AI changing.

[Ben Affleck]

There's a lot more fear because we have the sense that's existential dread. It's going to wipe everything out.

[Devin Joseph]

Right?

[Ben Affleck]

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 GPT5 about 25 times percent better than chatGPT4 and costs about four times as much in the way of electricity and data. So those nicely 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 were 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 your theory on that, Mattie? You know, being in the bank.

[Matty Belichick]

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 archives, Google or Anthropic bought books to scan books to get additional data because they couldn't find anything else on the Internet. So they've really maxed out that aspect or that access. That's the first axis. And that has been yielding really major improvements along the way. The same thing happened with compute. 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? You know, like, 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?

[Matty Belichick]

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, like, a collaborative setup where they would, like, 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. Like, 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 these different tasks. 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 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 like it didn't happen. So like, and we explore one theory of that which is by this anthropologist David Graeber, who insists that there's sort of like all these bullshit jobs in the economy. And so like we'll just, we just replace the jobs with like 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 going to 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 said 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 gbt. They discovered, like, oh, we can get hundreds of millions of users, and now it's a race to get a. 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 your. Your annoying middle manager. It's kind of like, wait, what are you. What do you do out?

[Matty Belichick]

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. 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 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? I'm Manny. 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 use case for this kind of of stuff, it was human enough.

[Devin Joseph]

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

[Manny Fadal]

No such thing as a production of Kaleidoscope content. Our executive producers are Kate Osborne and Mangesh. The show was created by Manny Fadal, Noah Friedman and Devin Joseph. Theme and credits Song by me, Manny Fadell Mixing by Steve Bone. Our guests this week were Evan Ratliff and Matty Bocheck from the podcast Shell Game. You can listen to all of season one and two wherever you listen to podcasts. Visit Nosuchthing show to subscribe to our newsletter. If you have feedback for us or a question, our email is mannynoadevonmail.

[Matty Belichick]

Com.

[Manny Fadal]

Or if you're in the U.S. you can also leave us a voicemail by calling the number in our show notes. We'll be back next week with a new episode.

[Evan Ratliff]

No such thing.