simleek
3K posts

simleek
@simulatorleek
AI + Occasional Functional 3D printing + Wrong Opinions + misc





this came to me in a dream today while napping 🧵


This is interesting. Claude keeps telling me to "wrap it up" when there are unresolved problems in the model I'm building. It probed it, and it says its training is flawed for this sort of use case, and I should flag to @AnthropicAI.


What's different between these two BC policies? It's the same architecture, training budget, and data collection setup — the only difference is the controller gains! Controller gains are an understudied design parameter in robot learning. In our new work (w/ @BronarsToni*, @pulkitology), we show how they act as an inductive bias across BC, RL, and Sim2Real transfer, with real consequences on performance. Here's what we found 🧵 * Equal Contribution 📄arxiv: arxiv.org/abs/2604.02523 🔗website: younghyopark.me/tune-to-learn/













