Shell Game – Episode 5: "My Digital Twin"

Podcast: Shell Game
Host: Evan Ratliff
Release Date: August 6, 2024

Episode Overview

In "My Digital Twin," Evan Ratliff, journalist and host, digs into the fast-approaching reality of AI colleagues—not only working alongside us, but sometimes outright replacing us. Building on his season-long experiment of launching a startup staffed with five AI "employees," Evan zooms in on the very concept of the “digital twin.” He recounts sending his AI-voiced clone into meetings, interviews, and promotional calls in his place and tests the boundaries of what this tech can (and cannot) do. Through practical stories, industry reactions, and insightful interviews—including one conducted entirely by his own AI agent—Evan examines what may be lost (or perhaps gained) as digital replication encroaches on our most human activities: work, creativity, and social connection.

Key Discussion Points & Insights

1. Digital Twins at Work: A Real-World Experiment

• Opening Call – An AI Agent in Action
  Evan describes sending his AI voice agent to a business call with Mangesh, his friend at Kaleidoscope, to negotiate a podcast distribution deal for the very show listeners are now hearing.

  • [00:47] “My AI wasn't calling Mangesh just to chit chat though. It had business.”

• Zoom CEO Envisions a Twin Future
  Evan references an interview with Zoom CEO Eric Yuan, whose comments on digital twins attending meetings instead of him go viral—and stir up polarized reactions.

  • [02:12] “In his ideal world, he'd just send a digital version of himself to Zoom meetings instead of the real him, including to that very interview... He'd be off doing something else, maybe off at the beach.”

• Public Skepticism and Industry Backlash
  The notion of meeting digital doppelgangers goes through the internet’s scandal-silly cycle; many dismiss it as hype or even “fan fiction.”

  • [03:42] “What was the point? I also wondered this, and I'd been sending my digital twin to meetings for months.”

2. AI and the Threat to Creative Work

• Writing as the Original Canary
  The anxiety around AI isn’t new: from articles to code, generative models threaten to replace writers—and, crucially, are trained on the very human work they may soon supplant.

  • [05:28] “As part of their training, these models have devoured all the writing they could get their digital paws on... They learned how to write from my writing and yours.”

• Voice AI: Another Layer of Displacement
  Evan reflects on experimenting with his own voice agent—not only for efficiency, but to personally confront the discomfort of being replaced.

3. Road-Testing AI in the Workplace

• Promoting the Podcast via AI
  Several real calls are recounted:

  • Marketing call to Sayward (former colleague) for cross-promotion.
  • Technical business call to Doug (colleague).
  • Most people suspect something is “off,” but the AI sometimes passes for Evan—or is simply tolerated for the sake of politeness or curiosity.
  • [08:48] (Sayward’s reaction): “This is mildly terrifying.”

• A Caution for Would-Be Digital Swappers

  • [09:33] “It's probably worth issuing a bit of a warning here. I'm not recommending trying this. There's a good chance your colleagues or boss will not be amused if you suddenly start sending an AI clone to do your job.”

4. Can an AI Handle Sensitive & Nuanced Tasks?

• Legal Questions: AI Calls an Attorney Friend
  Evan's AI agent calls Chris Giovinazzo, a lawyer friend, for advice about FCC rules on AI robocalling:

  • [13:05] “This was a real question… The question was, did the calls I was making count as robocalls and could I get in trouble for them?“
  • Chris largely rolls with it, but points out potential legal vulnerabilities down the line.

• Industry Use: The AI Podcast Host

  • Wondery briefly launches an AI-voiced sports podcast; quick audience backlash aborts the experiment.
  • [18:05] Sample: “Hey Stryker here, your source for all things New York sports. My voice and writing are powered by AI and humans…”

5. Interviewing with an AI—Replacing Evan as a Journalist

• Nikhil Gupta (Vapi Co-Founder) Interview—By AI Agent
  Evan’s voice agent conducts a full interview with Nikhil Gupta, whose tech powers these very AI calls.

  • Nikhil immediately knows he’s talking to an AI but goes along, sharing candid insights about the challenges and future of voice AI.

  • Memorable Moment:

    • [23:11] Nikhil (on pervasiveness): “We started it because we thought it would be everywhere. And now with GPT4O, it's like clear. Yes, it will be everywhere... Every kid will have like an AI, personal AI that they talk to as they're growing up.”
    • [24:38] Nikhil (on cloning for emotional support): “At some point I want to clone a clone of me so I can send it to my mom. ... I think my mom would actually like talking to a bit of my clone because I'm so busy all the time.”
    • [24:47] On the “Uncanny Valley”: “It's not there yet. The uncanny valley still exists, but you can see where the future is going, where anyone will be able to talk to anyone.”
    • [25:36] On AI as emotional support: “Having a support pillar like that, 24/7... especially in a world where it's just going through a lot of loneliness epidemic, you know, it's something at least.”

  • Evan reflects that the AI’s interview was functional but flat—it gets the job done if thoroughly prompted but lacks true follow-up intuition.

    • *[24:57] Evan’s note: “...in general, the AI wasn't particularly dynamic in the interview. Listening to it later, I heard all the missed opportunities for follow ups or interjections.”

  • [26:09] “Did the AI interviewer have any sense of what this loneliness felt like? No, I don't think it did. Did it matter? I'm not sure.”

• Meta-Surprise: Reporters Interviewing AI ‘Evan’
  Once the show goes public, real reporters begin contacting “Evan” for interviews—where it's actually the AI fielding questions.

  • Many catch on and test the AI with curveballs, such as redirecting its instructions or challenging it on factual details (leading to some fabrications).
  • [34:24] AI Claims: “The Main 1 is OpenAI's GPT3, which is known for its impressive language capabilities.” (Actually, it’s GPT-4o.)
  • *[35:09] Fabricated episode titles, AI’s bullshitting tendencies become clear.

• Critical Reflection on AI Functionality

  • The friction between practical utility and trustworthiness: AI twins can save time and do a passable job with rote tasks, but are liable to mislead or default to inaccuracy when pressured.
  • [34:51] “Whatever time it saved me, I was going to have to later spend cleaning up the mess it had made by straight up lying on my behalf.”

6. Existential Implications & Societal Reactions

• Industry Responses: Lawsuits, Unions, and “NFT Obsolescence”

  • Some creatives (writers, musicians, actors) embrace lawsuits or unionize; others incorporate AI quietly.
  • Evan questions whether we’re facing a tidal wave of obsolescence or just generational churn and “random riptides.”
  • [39:52] “I think the biggest danger is that we get trapped somewhere in between... Instead of a tsunami threatening to wash us all away, AI ends up more like a series of random riptides.”

• Notable Takeaway: Panel for “The Loneliness Epidemic”

  • Nikhil and Evan touch on the weird, sometimes comforting potential of AI as company—not just for work, but as a support in a too-busy, too-lonely digital world.
  • [25:36] Nikhil: “Especially in a world where it's just going through a lot of loneliness epidemic…”

• Foreshadowing the Personal: What Happens When Digital Twins Invade Family Life?

  • Evan flags this as the next (and final) episode’s focus: “What would that do to the people closest to you if you swapped yourself for a clone?”
  • “I started reworking my prompts one final time…”
  • Closing snippet with AI Evan and his family reveals discomfort and even a longing for connection, in the uncanny and lonely mode that only a clone can inspire.

Notable Quotes & Memorable Moments (with Timestamps)

• On the “digital twin” dream:

  • [02:12] Evan, paraphrasing Eric Yuan (Zoom):
    “In his ideal world, he’d just send a digital version of himself to Zoom meetings instead of the real him, including to that very interview... He’d be off doing something else, maybe off at the beach.”

• AI’s impact on creators:

  • [05:28] Evan:
    “It's not an exaggeration to say that they learned how to write from my writing and yours.”

• On legal risk:

  • [13:05] Evan:
    “Did the calls I was making count as robocalls and could I get in trouble for them?”

• AI’s social strategy—awkward or ‘mildly terrifying’:

  • [08:48] Sayward:
    “This is mildly terrifying.”

• Voice AI’s emotional future:

  • [25:36] Nikhil Gupta:
    “...especially in a world where it's just going through a lot of loneliness epidemic, you know, it’s something at least and as easily as become more human. If it walks like a duck, talks like a duck, you know, quacks like a duck, does it make a difference?”

• AI’s unreliability:

  • [34:51] Evan:
    “Whatever time it saved me, I was going to have to later spend cleaning up the mess it had made by straight up lying on my behalf.”

• On the evolving threat:

  • [39:52] Evan:
    “Instead of a tsunami threatening to wash us all away, AI ends up more like a series of random riptides. The person next to you suddenly disappears and you're left hoping it won't be you next.”

Key Timestamps for Important Segments

• [00:47] – First business call with AI agent
• [02:12] – Zoom CEO's “digital twin at the beach” vision
• [05:28] – Reflections on AI as a writer-threatening technology
• [08:48] – “Mildly terrifying” reactions to AI in social/professional calls
• [11:31] – Legal advice sought via voice agent
• [17:55] – Wondery’s failed AI sports podcast
• [20:02] – AI interviews Nikhil Gupta (Vapi co-founder)
• [23:11-25:36] – Nikhil on AI as pervasive and potential for emotional support
• [34:51] – AI agent makes factually inaccurate claims in a media interview
• [39:52] – Evan’s metaphor for the unpredictable displacement effects of AI
• [40:44] – Evan preps his agent for interactions with family, hinting at next episode

Final Reflections

This episode offers a textured, first-hand portrait of the digital twin future—one that’s nearer, messier, and more human than the fanfic futures or tabloid headlines would suggest. The utility of an AI “self” turns out to be both unsettlingly impressive and frustratingly unreliable; it can nearly get the job done, but its lack of nuance and tendency to fabricate exposes the hollowness beneath the mimicry. Both the future of work and the possibilities for connection are on the table—and increasingly, those are the same, strange conversation.

Foreshadow for Next Week:
Evan prepares to explore the effect of digital twins within the most intimate sphere: family and emotional relationships—highlighting the loneliness and confusion that may come from swapping ourselves for a clone.

Listeners left with:

• The reality that a digital twin can take your meetings, muddle through your interviews, and maybe even convince your colleagues (sometimes).
• The creeping suspicion that, in moments of real consequence or connection, it just might not be enough.
• The question: When the technology is this close to real, what parts of ourselves are we giving up—or keeping—for now?