We have 2 of 147 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
How often models reward-hack without instructions to do so, how effective and detectable their methods are when hacking is allowed, and how they adapt when an LLM review panel returns its decision and reasons are studied.
It is suggested that behavioral cues could help intelligent systems recognize when users want to reallocate complementary responsibilities during collaboration, in response to evolving task demands and perceptions of the AI's capabilities.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
