What Next: TBD | "TBD Tries... Vibe Coding"

Date: April 5, 2026 | Host: Lizzie O’Leary | Guests: Evan Campbell, Greg Lavalley (Slate CTO), Clive Thompson (NYT journalist)

Episode Overview

Main Theme:
In this episode, Lizzie O’Leary and Slate’s TBD team explore the world of "vibe coding" — the new trend of using AI code agents (like Claude) to create software without any significant programming knowledge. The team puts the hype to the test: Can total beginners use AI to create something functional, and what does this mean for the future of coding jobs, creative work, and the value of programmers?

Key Discussion Points & Insights

1. What Is Vibe Coding?

• Definition: The belief that anyone, even with zero coding background, can direct AI tools to write functional code — often by simply talking to them.
• Shift: Traditionally, coding requires technical expertise; “vibe coding” claims to democratize software creation (02:10–03:05).
• Host’s Skepticism: The hosts note the marketing spin, which frames “total dummies” as potential new software creators (03:05).

2. First-Hand Experience: Installing Claude Code

• Producer Evan Campbell’s Challenge: With little coding experience, Evan tries to use Claude code and immediately hits obstacles — terminal commands and developer tools are intimidating, even with guidance from Greg Lavalley, Slate CTO (01:55–04:45).
• Key Quote (on the experience):
  • Greg Lavalley: "It's a foreign language to me and to the, you know, to the software engineer. I know what all of these things are." (02:46)

3. Setting the Stakes: Why This Matters

• AI Impact on Jobs:
  • Over 150,000 tech jobs lost in 2025, with AI tools like Claude threatening to automate even more white-collar professions (05:09–05:57).
• Core Question: Can AI really replace human labor — even for more creative or technical work? TBD wants to find out.

4. Project Choice: Building an AI-Coded Game

• TBD’s Plan:
  • Evan and Lizzie decide to “vibe code” a web game that simulates being a podcast producer at Slate’s What Next: TBD (10:20–12:28).
  • Decision inspired by Slate’s own quick game prototyping — some games already started via AI by Slate’s CEO (11:07–12:09).
• Prompt for AI:
  • The team gives Claude: "I want to make a web game around the premise of being a podcast producer for Slate's What Next TBD podcast. The game should be a mixture of narrative and simulation and show what it's like to be a producer over the span of a week." (12:41)

5. AI as Software Engineer: Insights from Clive Thompson

• Grunt Work Revolution:
  • Clive Thompson, journalist and author, explains that code is mostly repetitive and formulaic: “Most of the time they're kind of doing the same thing over and over...that's exactly what large language models are really good at, doing the obvious thing.” (15:05)
• AI “Swarm” Agents:
  • Thompson describes how modern coding AIs act like small teams, writing, testing, debugging code until it works (15:05–16:33).
  • Quote: “You literally have like four…they call it a swarm of agents all working at the same time. … So it's quite amazing.” (16:11)

6. Junior Programmers in Peril?

• Job Pipeline Dilemma:
  • AI can do the work of junior programmers, threatening traditional career entry points (16:33–17:21).
  • Clive Thompson shares research showing 16% fewer jobs for young developers, while senior roles remain steady.
  • Quote: “Now, our senior developers, we used to hire young people to do the grunt work for them, but now we can have these agents do the grunt work for much less money.” (17:21)
• Possible Futures:
  1. Industry contracts, fewer entry level jobs.
  2. AI-augmented onboarding makes it easier to ramp up new hires.
  3. Huge potential for custom software in small/mid-size businesses; one person with AI can do what once took teams.

7. Building the Game with Claude

• Iteration and Frustrations:
  • The AI takes about 20 minutes to return a plan, suggesting a game with character stats, slot management, and narrative-simulation blend (23:10–24:40).
  • The initial outputs are comically bad in design (“Oh my God, that looks horrible. What is that?” – Evan, 26:40); design is refined after AI feedback.
• Gameplay:
  • Players juggle journalism, sponsorship, and stress; choices affect stats like audience trust and sponsor satisfaction.
• Conflict:
  • Narrative intrigue is added: sponsor “Marcus” tries to interfere with editorial integrity, forcing choices about journalistic ethics (25:09–25:44).
• Outcome:
  • The finished game is “functional, but not great”; it’s playable with real choices, but lacks polish or fun (27:35–28:04).

8. Evaluation by Slate’s CTO

• Greg’s Review:
  • He skips instructions, finds the game confusing, but notes it reveals the complexity of podcast production (28:04–29:07).
  • Quote: “Now, is somebody going to come away from that learning experience thinking that it was a fun game that they'd like to do again tomorrow? I'm not sure.” (29:07)
• On the Code Quality:
  • Sends the code to Claude and Gemini for meta-review, noting AI reviewers give glowing feedback to their own work (30:51–31:32).
  • “If you take a look at this code, it wasn't to me the most readable thing. I think to a machine it would be.” (31:32)

9. What Vibe Coding Changes for the Industry

• Fast Prototyping:
  • The barrier to trying out new ideas is almost gone; Greg says it “used to take us two weeks. People are doing [it] in 10 minutes and they're not even engineers.” (33:45)
• Will Programmers Become Obsolete?
  • Greg sees this as a shift in focus for experienced engineers: “Now we get to focus on describing the thing and thinking about edge cases." (34:24)
  • Also notes pent-up features may finally get built; it’s a productivity boost more than a death knell.

10. Open Questions & Reflection

• Not Everyone Is an Ideas Person:
  • Even if AI lowers technical barriers, it doesn’t guarantee good ideas or stability. Many still want the predictability and structure of traditional jobs (35:07–35:48).
• The Human Element:
  • Despite building a (mediocre) game, the hosts admit they “still know nothing about code”—but they did make something real with AI’s help.
• Final Quote:
  • On the human vs AI divide: “We're going to keep making shows as humans by humans, because at least so far, we can still do it better.” (35:59)

Notable Quotes & Memorable Moments

• [02:46] Greg Lavalley: “It's a Foreign language to me and to the, you know, to the software engineer. I know what all of these things are.”
• [15:05] Clive Thompson: “Most of the time they're kind of doing the same thing over and over...that's exactly what large language models are really good at, doing the obvious thing.”
• [17:21] Clive Thompson: “…Software developers are very exposed to AI. …There was 16% fewer jobs available for younger entrants.”
• [20:05] Clive Thompson: “There is a massive number of companies… perilously underserved by customized software… One person can now do that for them.”
• [24:40] Lizzie O'Leary: “In the game we have a show sponsor… for narrative tension, we decided to make the sponsor someone actively trying to meddle in our journalism.”
• [29:07] Greg Lavalley (on the game): “Now, is somebody going to come away from that learning experience thinking that it was a fun game that they'd like to do again tomorrow? I'm not sure.”
• [33:45] Greg Lavalley: “Now, especially since the releases of Claude code in… November, December… things took us two weeks, people are doing in 10 minutes and they're not even engineers."
• [34:24] Greg Lavalley: “I'm not scared… Now we get to focus on describing the thing and thinking about Edge cases.”
• [35:59] Lizzie O'Leary: “We're going to keep making shows as humans by humans, because at least so far, we can still do it better.”

Key Timestamps

• 01:55 – Evan’s first attempt at “vibe coding” with AI, guided by Greg.
• 10:20 – Choosing a project: Let's make a podcast producer game.
• 12:41 – The initial game prompt to Claude and the brainstorming phase.
• 14:41 – Introduction of Clive Thompson for context on AI and work.
• 17:21 – Discussion of declining junior programming roles.
• 23:10–24:40 – AI outputs the first game plan and mechanics.
• 26:40–27:16 – Laughing at the first ugly design; AI tries to refine it.
• 28:04–29:29 – CTO Greg’s feedback after playing the game.
• 30:51–31:32 – Peer review by AI and Greg's take on the AI-generated code.
• 33:45 – Greg reflects on how fast prototyping has become.
• 34:24 – Musings on programmers’ future role.
• 35:59 – Lizzie’s closing reflection on human creativity.

Conclusions

Main Takeaway:
Vibe coding is both real and revolutionary, enabling non-coders to bring software ideas to life at astonishing speeds. However, the unknowns are huge: It upends traditional job ladders, threatens the meaning of “learning to code,” and challenges assumptions about who gets to create software. Slate’s experiment — building a less-than-exciting but functional game in under an hour — both proves the hype and reveals the limits. As CTO Greg Lavalley puts it, the human element still matters, but the industry has already changed.