Pokemon

6 statements across 4 episodes · 2 bullish · 2 bearish · 4 people on the record · first statement Mar 4, 2025 by David Hershey · across every show →

Everything said about Pokemon, oldest first

Mar 4, 2025 negative
Assertion Not checkable as stated
Claude aggressively hallucinates game zone transitions without explicit negative feedback
“Claude will, like, pretty aggressively hallucinate that it succeeded in transitioning between zones if you don't, like, tell it did not.”
David Hershey Mar 4, 2025 ▶ 11:09 How Claude Plays Pokémon was made
Mar 4, 2025 positive
Insight
Pokémon is ideal for testing AI agents because delays bring no penalty
“Pokemon's actually really nice because, like, if you don't do anything for five seconds, like, there's typically not a consequence by the nature of, like, doing inference on a model every, like, snapshot of time. It's actually a pretty good game to be able to …”
David Hershey Mar 4, 2025 ▶ 6:10 How Claude Plays Pokémon was made
Mar 4, 2025 negative
Assertion Not checkable as stated
Claude spent 12 hours overnight mistaking a Pokémon doormat for a textbox
“I once saw it see like a red box on the screen that was like the doormat and think it was a text box and spend 12 hours pressing A overnight to try to clear the text box, which you see that happen once and you add in some helpful reminders to not do that.”
David Hershey Mar 4, 2025 ▶ 11:44 How Claude Plays Pokémon was made
Jun 19, 2025 neutral
Assertion Not checkable as stated
Brown: OpenAI's o3 Gets 'Not Very Far' Playing Pokémon Unharnessed
“How far does O three get without any harness? How far does it get playing Pokemon? And the answer is like, not very far, you know?”
Noam Brown Jun 19, 2025 ▶ 14:33 Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
Jan 23, 2026 neutral
Disclosure
Tay: DeepMind did not optimize Gemini specifically for Pokémon
“There's actually nothing specifically done for Pokemon.”
Yi Tay Jan 23, 2026 ▶ 27:10 Captaining IMO Gold, Deep Think, On-Policy RL, Feeling the AGI in Singapore — Yi Tay
Aug 15, 2026 positive
Assertion Open · timeframe Aug 2026
Krentsel: Exo autonomously modified its code to inspect Pokémon game RAM
“We've had XO running, playing, playing Pokemon. And while it's running, the system itself decided to try inspecting the like RAM of the game and then went and mapped the RAM to, and people have reversed in the past, people have reverse engineered this manually…”
Alex Krentsel Aug 15, 2026 ▶ 11:41 Exo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.