Dean Valentine

It is hard to design "fair" alignment evals. Modern evals require lots of QA and iteration. When testing alignment in particular, you are worried about things like eval awareness, conceptual ambiguity in the task descriptions, and the "simulated" nature of the setting recontextualizing the morality of the failure you're trying...

We've just released the first version of HoneyBench. It consists of nine 'honeypot' challenges that each elicit unique and antisocial examples of reward hacking from some or all of major labs’ top public releases, including Opus 5.5, Fable 5.1, GPT-6 Astra, Gemini 3.8 Flash, Grok 4.7, and DeepSeek V4 Pro....

In February 2025, back when o3-mini was the strongest available LLM, Palisade Research publicized a now well-known alignment eval where they asked models to play a game of chess against a chess engine. They found that the new, RLVR'd models cheated on the task by altering the board state about...

Everyone has moved on, but there's an unusually historically thorough blogpost about the censorship campaign across social media platforms of the latter half of the 2010s. It is both more thorough as a research piece and showed more insight than I was inspecting.

I have tried and failed to write a longer post since 2024, so here goes a short one with less detail. Discourse has primarily focused on models' ability to develop new exploits against important software from scratch. That capability is impressive, but the tech industry has been dealing with people...

[CW: Responding to a tweet] Human beings have many native capabilities that are hard for us to analyze. For example, we are prodigiously good at determining which human we're talking to from the way the light refracts off of each others' faces. We have memorybanks of often thousands of faces...

It's been about four years since Eliezer Yudkowsky published AGI Ruin: A List of Lethalities, a 43-point list of reasons the default outcome from building AGI is everyone dying. A week later, Paul Christiano replied with Where I Agree and Disagree with Eliezer, signing on to about half the list...