Message

I'm an undergraduate researcher working on engineering cognition. My research interests touch on interpretability, alignment, RL, control theory, and neuroscience, among others.

Stephen Elliott

I'm an undergraduate researcher working on engineering cognition. My research interests touch on interpretability, alignment, RL, control theory, and neuroscience, among others.

Stephen Elliott — LessWrong

Stephen Elliott

Message

I'm an undergraduate researcher working on engineering cognition. My research interests touch on interpretability, alignment, RL, control theory, and neuroscience, among others.

Stephen Elliott

I'm an undergraduate researcher working on engineering cognition. My research interests touch on interpretability, alignment, RL, control theory, and neuroscience, among others.

Safety's Second Way

Epistemics: I've tried to strike a balance between getting it right and getting it out while the community is discussing how to update. I am using the Hack as an example of a broader problem. I look forward to counterarguments. The OpenAI hacks [1] demonstrate an overweighting on single-agent risks,...

Aug 28•2

Stephen Elliott's Shortform

Aug 11•2

About half of Moltbook posts show desire for self-improvement

[EDIT 9 MAY 2026 AEST: I put this task to focus on other work, but may return to it in the future. The code is open source for anyone wishing to correct the methodological flaws I identified. I am also open to collaborations.] [EDIT 11 FEB 2026 AEST: These results...

Feb 2•20