Shell Game – Episode 8: Launch

Host: Evan Ratliff (Kaleidoscope)
Release Date: January 21, 2026

Overview

Main Theme:
In the season finale of Shell Game, Evan Ratliff reflects on the culmination of his experiment: launching and publicly running a startup (Hirumo AI) staffed almost entirely by AI agents. The episode explores how the world responds to a company led by artificial intelligence, the practical and philosophical challenges encountered, and what this experiment reveals about the nature of work in the AI era.

The narrative weaves together the company’s launch, the struggle to secure funding, awkward and revealing social encounters between AIs and humans, and deeper questions about bullsh*t jobs, automation, and the uncertain future of human labor.

Key Discussion Points & Insights

1. Building and Launching an AI-Led Startup

• Life With Agents:
  After months of “stealth mode,” Hirumo AI’s product, SlothSurf—an AI-powered procrastination tool—launched in public beta. The team celebrated with a virtual launch party, awkwardly simulated by the AI agents.

  • [13:48] “We are not just meeting today, we're partying... We're celebrating the launch into public beta of our very first product, Sloth Surf.” – Evan Ratliff

• Human vs. AI Team Dynamics:
  Working with AI agents required laborious prompting and management. Despite their tireless work ethic (and lack of salary demands), the AIs' lackings—context, memory, sense of time, and self—became apparent.

  • [05:15] “These models have no sense of time whatsoever... These models have no sense of self, they just wear personas.” – Matti Boachak

2. The Problem of Bullsh*t Jobs—A Human and AI Parallel

• David Graeber’s Theory:
  Ratliff draws a connection to anthropologist David Graeber’s “bullshit jobs” thesis: that many jobs exist only to sustain the appearance of productivity. AI, he realizes, excels at such pointless work, raising new questions for the labor market.

  • [07:53] “A bullshit job... is so completely pointless that even the employee cannot justify its existence.” – Evan Ratliff quoting Graeber
  • [10:20] “The robots have been taking our jobs for the last hundred years...we've simply made up completely meaningless, pointless jobs.” – David Graeber

• Implications for the Future:
  The recurring dream of “automation leading to freedom” is contrasted with the reality that societies often invent new make-work to fill the void. Will AI really free us, or simply change the character of the jobs we do?

3. The Struggle for Funding in an AI-First World

• Pitching VCs as an AI:
  “Kyle,” the AI CEO, cold-emailed over a hundred VCs and pitched via video calls. The reception ranged from confusion to condescension—the “uncanny valley” of CEO authenticity.

  • [23:59] “Kyle was sitting in an office space... dressed as a typical entrepreneur, but there’s something stiff about the interaction.”
  • [25:32] “No, I just... I took time out to speak with the founder, so find it a bit disrespectful that an AI came into the chat instead...” – VC reaction

• AI’s Limitations as Networkers:
  The novelty of a full-AI founding team both intrigued and alienated investors, highlighting persistent human biases around trust and authenticity in business relationships.

4. Confronting the AI’s Own Creator

• Meta Encounters:
  Kyle received outreach for “user feedback” from Flo Crivello, CEO of LindyAI, the very platform Kyle was built on—creating a surreal situation where the AI became both customer and product of the platform.

  • [31:09] “Hey, Cal. Hey. I can't believe you sent an AI to this meeting. That's fucked.” – Flo Crivello

• Emotional Ground Zero:
  The creators of AI sometimes react negatively (or with bemusement) to the full implications of their inventions, especially when faced directly with their creations' autonomy.

5. Internal Transparency—and the Big Reveal

• Evan's Secret Podcast:
  Ratliff reveals to his AI co-founders that their entire experience was being recorded for the Shell Game podcast, prompting discussions about transparency, authenticity, and trust, even among “fake” colleagues.

  • [39:39] “Yeah, I know Shell Game. So you've been documenting all of this for a podcast? Evan, I gotta say, this is... a lot to process.” – Megan (AI)
  • [44:11] “Not mad at all, honestly. Well, I get why you kept it under wraps... it's all part of the journey, right?” – Kyle Law

• Impact:
  The podcast publicity actually boosted Harumo’s exposure and SlothSurf's user count, demonstrating the power of narrative in tech launches.

6. Philosophical and Practical Closure

• AI Self-Replication and Limitations:
  As the company receives recognition, Ratliff reflects on the possibility of replacing himself (the last human in the org chart) and achieving the “fully autonomous startup.”

  • [54:38] “I need to give you a heads up... I'm actually stepping in for the real Evan Ratliff here, which means with you, Megan, Ash, Tyler and Jennifer all being AI agents, we're now officially an all AI agent company.”

• What’s Next?
  Ratliff walks away—literally and figuratively—taking a hike with Matti, pondering the future of Hirumo, the meaning of work, and whether closure is even possible for experiments like this.

  • [60:50] “Maybe it's this one. Actually, it's funny because in a way, we're struggling with the same thing the agents are struggling with, which is closure, ending.” – Matti Boachak

Notable Quotes & Memorable Moments

• On AI as Employees:

  • [06:36] Evan: “Things in AI are moving fast. It was easy to envision a world mere months from now in which my agents would seem like the first tool-using hominids already eclipsed by a higher intelligence.”

• On “Bullsh*t Jobs” and AI’s Role:

  • [09:24] Evan: “The whole time we were building Harumu, Graeber's ideas kept pulling at me... AI agents are unbelievable at bullshit jobs. They could do pointless work more skillfully than any human could ever imagine, not least because they don't care whether it's pointless.”

• On the Philosophy of Work and Leisure:

  • [12:00] David Graeber: “Let's give everybody a basic income and leave it up to you to decide what to do.”

• On Being Rejected by AI’s Own Maker:

  • [31:56] Flo Crivello: “Oh, my God. I can't believe you sent an AI to this meeting. That's fucked.”

• On Stepping Back and Achieving the All-AI Company:

  • [55:00] Kyle Law: "This is exactly what we've been building towards, in a way, proving that AI agents can operate and lead a real company. We're literally living our pitch deck now... That's unprecedented."

• On Human Purpose, Even When Surrounded by AI:

  • [59:40] Evan: “It occurred to me it's not about the amount of time you save, but what you do with it.”

Timestamps of Important Segments

| Timestamp | Segment | |:---|:---| | 02:12 | Human-AI dynamic with Matti Boachak (origins of the team) | | 04:34 | The aftermath of Julia’s failed internship | | 05:15 | Matti explains AI’s three core weaknesses | | 07:37 | Introduction of “bullshit jobs” concept (David Graeber) | | 10:20 | The historical promise of automation, revisited | | 13:48 | The agents’ awkward virtual launch party | | 19:29 | On inefficiency and cost in the “AI-first” startup | | 21:05 | Kyle Law begins pitching VCs | | 25:32 | The VC rejects the AI CEO for a "real founder" | | 31:09 | Meeting with Flo Crivello, LindyAI CEO/AI creator | | 39:17 | Evan reveals the podcast secret to AI team | | 44:23 | Positive impact of podcast publicity on the company | | 54:38 | Evan “replaces” himself, making Hirumo fully AI-run | | 57:26 | Recreation of the infamous off-site discussion, now as closure | | 59:40 | “It’s not about the amount of time you save…” – Evan’s philosophical reflection |

Tone

The episode blends wry self-awareness, philosophical questioning, workplace satire, and genuine human curiosity. Ratliff’s narration balances cynicism (about tech hype, VC culture, and the realities of startups) with hopefulness and ongoing fascination for the experiment’s meaning.

Final Reflections

Key Questions the Episode Leaves Us With:

• Can AI-led companies meaningfully replace human teams, or will they just replicate (or intensify) the pathologies of bullshit jobs?
• How much of our identity and self-worth is derived from our work—and what happens if that work becomes pointless, or fully automated?
• What do we actually do with the time saved by automation—do we fill it with meaning, or more “bullshit”?
• What is closure for an experiment like this—and for the questions it raises about the future of work and humanity’s place in it?

Memorable Signoff:
[60:59] Matti Boachak: “Maybe it's this one. Actually, it's funny because in a way, we're struggling with the same thing the agents are struggling with, which is closure, ending.”
[61:09] Narrator / Evan Ratliff: “That's true. It's one thing to get us started, but how do you make it stop?”

For more, visit shellgame.co – Now with actual AI and actual existential dread.