David Hershey

9 statements across 2 episodes · 3 bullish · 0 bearish · 1 people on the record · first statement Mar 4, 2025 by David Hershey · said 4 times in 2 episodes since 2025 · across every show →

On the record as a speaker too: David Hershey's record, appearances and statements → this page counts the times other people say the name.

Mentions by year

brought up most by Shawn Wang (3)

tap a year for its mentions
0021422025episodesmentions
0122025episodes it came up in
0011222025episodesmentions per episode
2025 4 mentions in 2 episodes 2 per episode

every mention, scene by scene, with the transcript →

Everything said about David Hershey, oldest first

Mar 4, 2025 neutral
Disclosure
The Claude Plays Pokémon knowledge base is simply a prompted Python dictionary
“I think my knowledge base is frankly, like, kind of kludgy of an implementation right now. Like, it's, like, more or less a Python dictionary that's appended to the prompt.”
David Hershey Mar 4, 2025 ▶ 26:50 How Claude Plays Pokémon was made
Mar 4, 2025
Disclosure
Upgrading Claude models in Pokémon primarily involves deleting prompt scaffolding
“Literally every model that has come out with Pokemon, like, the main change that I have made to this agent is deleting prompt stuff.”
David Hershey Mar 4, 2025 ▶ 22:51 How Claude Plays Pokémon was made
Mar 4, 2025 positive
Assertion Not checkable as stated
Prompting Claude to nickname its Pokémon caused it to exhibit protective behaviors
“And one thing we found when we started doing that is it got more protective of the Pokemon it nicknamed. Like, it's pretty obvious, like, when it catches a Pokemon, Now that it has a nickname, it will, like, go heal it right away if it's hurt, and that did not…”
David Hershey Mar 4, 2025 ▶ 25:13 How Claude Plays Pokémon was made
Mar 4, 2025 neutral
Insight
Measuring AI game progress is an integration test, not a unit test
“And so I think like how quickly it's able to make progress is actually a pretty reason or a reasonable like eval if a slightly expensive one to calculate. It's an integration test, not a unit test.”
David Hershey Mar 4, 2025 ▶ 37:04 How Claude Plays Pokémon was made
Mar 4, 2025 positive
Assertion Not checkable as stated
Claude 3.7 Sonnet uniquely generates meta-commentary reflecting on its perceptual errors
“And actually like one of the things that's most unique about. 3.7 sonnet that I've seen is like, it will have like meta commentary on what it's good at and bad at and it's knowledge base. Like I misperceived this thing. And so like, I need to be careful doing …”
David Hershey Mar 4, 2025 ▶ 26:23 How Claude Plays Pokémon was made
Apr 5, 2025
Insight
Hershey: Stacking Negative Scaffolding Instructions Degrades Agent Performance
“If you keep adding that type of instructions, you eventually make the model stupider. Like, if you add 50 of that type of instruction, you just end up, like, with the whole agent doing worse”
David Hershey Apr 5, 2025 ▶ 25:37 Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
Apr 5, 2025
Disclosure
Hershey Restricts Multi-Button Inputs After Claude Overwrote Ivysaur's Attack
“People who have watched the stream often complain about the fact that I don't let Claude press multiple buttons when there's dialogue on the screen anymore. That's because I watched a run, or a run, where it had an Ivysaur in Mt. Moon, and it had Tackle as its…”
David Hershey Apr 5, 2025 ▶ 7:58 Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
Apr 5, 2025
Assertion Not checkable as stated
Hershey: Eight Historical Images Yields Peak Performance for Game Agents
“At least in my harness, something like eight historical images is the best performance. More than that, and you start flirting with the space where, like, you get drop off in performance from, like, just having more tokens in the context, which is a thing that…”
David Hershey Apr 5, 2025 ▶ 23:52 Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
Apr 5, 2025 positive
Insight
Hershey: Newer Claude Models Tenaciously Keep Trying Rather Than Quitting
“This is, like, maybe the thing that is the best about the new models is they have a tendency to, like, tenaciously still try things.”
David Hershey Apr 5, 2025 ▶ 6:56 Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
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.