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?