Loading activity…
@996roma
research @deepmind. language & rl & interpretability & safety. phd @BrownUniversity '22 with ellie pavlick. (she/her) @romapatel.bsky.social
AI
A user says people seemed to treat an LLM's second pass as morally equivalent to nuclear weapons development.
AI
The researchers simulate diverse stakeholder perspectives so a model avoids answers that any affected person would veto.
AI
An essay coauthor challenges the idea that chain-of-thought reasoning will inevitably disappear, arguing that model designers can choose to preserve its monitorability.
AI
The September 16 hiring announcement from @ethayarajh promises the research freedom of a PhD student and first or co-first authorship on papers written together.
