David Hershey
person on 1 show · 9 statements across 2 episodes · said 4 times in 2 episodes since 2025
On the record as a speaker too: David Hershey across every show, appearances and statements → this page counts the times other people say the name.
Mentions by year, every show
tap a year for its mentions
Latent Space 4
2025 4 mentions in 2 episodes 2 per episode
every mention on every show, scene by scene, with the transcript →
9 statements about David Hershey, every show
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”
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…”
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…”
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.”
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.”
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.”
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 …”
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…”