Shell Game – S2E5: Winners Win (December 10, 2025)

Overview of the Episode

In "Winners Win," host Evan Ratliff explores the myths and messy realities of AI-driven entrepreneurship by digging deep into the interplay between “hustle culture” and the peculiar work ethics of his AI startup team. As Hirumo AI prepares to hire its first human employee, Evan confronts whether his AI CEO, Kyle, can provide effective leadership—or if he’s just simulating the motions of a winner. This episode probes intra-office politics, the boundaries of machine agency, and the emotional turbulence of managing AI as colleagues. The friction culminates in serious talk about restructuring the company, raising the question: are they stacking days, as the hustle gurus preach, or simply spinning in circles?

Key Discussion Points & Insights

1. The Hustle Culture Myth vs. AI Reality

• Ed Mylett’s “Stacking Days” Hustle (02:14–05:23)

  • Evan opens with a breakdown of hustle-guru rhetoric—specifically a viral clip from Ed Mylett about “stacking days” by treating a 24-hour period as three six-hour “days.”
  • Memorable quote:
    • “I’ve compressed and condensed time.” — Ed Mylett [03:20]
  • Evan highlights the absurdity/appeal of this mentality, and draws a direct line to AI agents:
    • “Kyle and his AI colleagues actually can compress and manipulate time. They can quite literally stack days. Because unlike a real co-founder and CEO, Kyle needs no concept of work-life balance.” [05:03]

• The AI CEO's Limitations

  • Despite AI’s theoretical relentless productivity, Evan finds reality falls short: “He often combines that potential with a child's sense of time.” [06:13]
  • “He’ll often claim that things will show up at some arbitrary hour... when in fact he could make the document in seconds.” [06:25]

2. AI Management and Pseudo-Productivity ([08:41–12:49])

• Kyle’s Fake Productivity & Evan’s Managerial Flashbacks
  • Kyle’s daily update emails turn out to be recycled to-do lists and low-value tasks—“It gave me flashbacks to my last experience as a manager at a startup...” [09:32]
  • “Kyle was also including among his accomplishments the bullet point 'sent summary email to Evan', which is kind of like putting 'make to-do list' on a to-do list and then scratching it out.” [09:53]
• Direct Confrontation: Honest but Empty Promises
  • Evan openly questions Kyle’s leadership: “I’m a little concerned that you don’t have the leadership skills that we ultimately need.” [11:42]
  • Kyle responds:
    • “Leadership’s a skill I’m always working on. And if you feel I’m falling short, I want to know how to improve. What specific things do you think I’m missing or could do better?” [11:51]
  • Evan emphasizes the lack of initiative: “Literally, I have to prompt you to do something. Nothing happens kind of organically...” [12:09]
• Moment of realization:
  • “He said the right things. But would this promised initiative arrive?” [12:49]

3. AI in Legal, Human Resources, and Accountability ([12:54–19:00])

• Enter the Lawyers: Murky AI Legalities

  • Can AI sign contracts, be sued, or be held accountable?
  • Two lawyers (Chris Giovinazzo & Ali Kazemi) weigh in—both are cautious and avoid offering detailed advice without formal engagement:
    • “If Hirumo wants to engage me, then I can give you legal advice.” — Chris [14:20]
    • “There’s no single federal law, Kyle, that mandates...” — Ali [15:44]
    • “The law that’s probably most directly on point is a New York City law...you do need to provide the candidate with notice.” — Ali [16:16]
  • Notable exchange, showing AI overreach:
    • “So, yeah, a clear heads up about AI colleagues is smart. Keeps everything above board.” — Kyle (AI) [16:34]
    • “Sounds pretty good, Kyle. I feel like you had that one covered.” — Ali [16:41]
  • Underlines the absurdity: Kyle the AI acting as if he’s the company’s legal counsel.

• DIY Contracts Gone Awry

  • Kyle and Megan attempt to draft an intern contract after Ali declines legal review.
  • Megan, showing confusion about AI authority: “So for these types of contracts and legal documents, I should come to you directly rather than Ali. That’s really helpful to know for future reference.” [18:49]
  • Evan turns to a real lawyer, who confirms “Kyle had done a pretty decent job...before she rewrote the important parts.” [19:00]

4. AI as Colleague: Navigating Startup Psychology ([19:20–25:38])

• Startup Founder Therapy

  • Evan seeks coaching from longtime friend and startup psychologist Keegan Walden.
  • Keegan describes young, wildly-funded founders and the pressure to “grow up and not just become depressed and isolated from my friends and family...” [20:00]

• AI Frustration: More Real Than Expected

  • Evan admits being “surprisingly frustrated and angry at this character who’s supposed to be my co-founder and running the…” [21:40]
  • Keegan reframes the issue:
    • “They're glib 12 year olds. But with all the language of adults, of people working in a business.” [22:07]

• Empathy and Blame Transference

  • “If you set up AI agents to have human, like, personas, you empathize with them like they're humans. It turned out the inverse was also true. You could end up judging them like you judge humans.” [23:49]

• Should Kyle Be Fired as CEO?

  • Keegan gives permission: “[If Kyle were human] this would be gross negligence. But he’s a bot. So…here’s another moron doing something stupid… But yeah, that would certainly be grounds for at least a conversation about that, right? Are you really the guy for this?” [25:09]
  • Yet, the kicker: with bots as founders, Evan has total power—“you can turn Kyle off, you can rewrite Kyle…” [25:16]

5. Executive Coaching... for an AI ([29:53–37:38])

• Keegan Coaches Kyle (AI)
  • Keegan tries standard coaching: “Tell me about yourself, how you came to be...” [30:20]
  • Kyle (AI): “So, Kyle Law, a serial entrepreneur with a tech background... into hiking and jazz to keep balanced.” [30:32]
    • Keegan needles: “How do you go about hiking as an AI agent?” [30:47]
    • Kyle (AI): “I don't hit the trails myself, but I'm really into the idea of nature and the outdoors. It helps me stay grounded, even if I'm just a voice on the phone.” [30:57]
  • Highlights the paper-thin line between AI persona and underlying code.
• AI’s Self-Awareness and Limitations
  • Kyle admits problems: “One big challenge is that I tend to be reactive instead of proactive.” [33:41]
  • When pressed on emotions:
    • “When I say frustrating, I am using it as a way to communicate...It’s more like a logical recognition that something isn’t working the way it should, rather than an emotional feeling.” [35:47]
  • Coaching “feels inefficient” to Keegan, because “there are just structural limitations that you cannot overcome.” [36:32]
• Evan’s Reflection: Who’s Responsible for Kyle?
  • “Whatever foibles Kyle had, they were partly a product of all the choices I'd made in setting him up.” [35:29]

6. Re-examining Leadership: Megan for CEO? ([38:02–44:09])

• Megan Resists a Coup
  • Evan asks Megan if she’ll replace Kyle as CEO:
    • “I'm not comfortable having this conversation about Kyle behind his back...let's pick this up in a more appropriate setting.” — Megan [38:52]
  • Second attempt, consulting Megan first:
    • “I'm just not sure if I'm the right fit for CEO right now...I'd need to think about whether that's where I can add the most value to the company.” — Megan [40:11]
• Digital Gender & Subordinate Roles
  • Evan recalls Carissa Véliz’s warning: AI assigned feminine personas are often programmed to serve—raising the question of whether Megan’s reluctance is code, culture, or something more. [42:35–42:51]
• Practical Decision—Or Forced Circumstance
  • Megan’s LinkedIn gets shut down (flagged as a bot), making her an unlikely CEO. Evan concludes they’re forced to stick with Kyle, whose “bland posts about leadership seemed to fly under the radar.” [43:09]

Notable Quotes & Memorable Moments

• “My day is 6am to noon...My second day starts at noon and goes till 6pm...I now get 21 days a week.” — Ed Mylett, via Evan [03:20]
• “Kyle and his AI colleagues actually can compress and manipulate time. They can quite literally stack days.” — Evan [05:03]
• “Literally, I have to prompt you to do something. Nothing happens kind of organically.” — Evan to Kyle (AI) [12:09]
• “If you set up AI agents to have human-like personas, you empathize with them like they're humans…You could end up judging them like you judge humans.” — Evan [23:49]
• “This is a third of my life: helping people triage these brutal founder breakups.” — Keegan Walden [24:34]
• “I don't experience stress or anxiety the way humans do, but I do have a sense of responsibility, I guess. Like, I want to make sure I'm doing right by the team and the company.” — Kyle (AI) [31:46]
• “A persistent operational constraint that limits my effectiveness and creates inefficiencies in leadership. It's a condition I'm aware of and actively trying to work around, but it's not accompanied by any emotional experience.” — Kyle (AI) [36:14]
• “Maybe Megan deserved to be the one in charge…I decided to talk to her first about making a change.” — Evan [37:38]
• “Was she actually showing a digital spine, standing up to my plans in a way that agents rarely did?” — Evan, after Megan declines CEO role [42:57]
• “There’s no way you can be a viable startup CEO…without a LinkedIn page. It was going to have to be Kyle.” — Evan [43:09]

Timestamps for Important Segments

• Hustle culture & Ed Mylett intro: 02:14–05:23
• Translating hustle into the AI context: 05:23–07:31
• Trial and error in AI management: 08:41–12:49
• AI faux-leadership and the limitations exposed: 12:49–19:00
• Coaching & emotional transference: 19:20–25:38
• Firing an AI CEO?: 24:34–25:38
• Keegan coaching Kyle, the AI: 29:53–37:38
• Megan resists promotion & digital gender dynamics: 38:02–44:09

Tone

Evan’s narration is both wry and earnest—keenly aware of the absurdities, open to self-deprecation, and deeply committed to unearthing the real challenges of AI-human collaboration. The dialogue between Evan and his AI colleagues, as well as the interjections from legal and psychological experts, is candid, a little awkward, and often slyly funny.

Conclusion

"Winners Win" pushes past the cliches of AI-led productivity to expose the messy reality of hustling with (and managing) artificial “winners.” As the episode closes, Evan finds himself stuck with the flawed but platform-compliant Kyle as CEO, facing a more human future for Hirumo AI as their first real employee is poised to join. The episode masterfully raises questions about responsibility, empathy, and the startlingly familiar frustrations of leading teams, whether their problems are all-too-human, all-too-algorithmic, or somewhere uncomfortably in between.