Hey everyone! We’re introducing Drone-Bench, a benchmark where AI agents code drones to complete a simple autonomous surveillance task. Drone-Bench is independent but based on Project…
Linkpost for my Substack piece, lightly adapted. Disagreement very welcome.What happenedCoefficient Giving (cG) announced a $1 billion gift to GiveWell on 23rd July. This increases a…
Reinforcement learning from verifiable rewards (RLVR) is the hot new thing in LLM training. It’s so hot, and people spend so much time talking about it,…
I believe there is a blind spot in the literature on the biggest risks to democracy from AI. The ones that come up most frequently include…
SummaryAY 2025-26 was an outlier year for Georgia Tech’s AI Safety Initiative (AISI), with 15+ members placed in AI safety roles. In this post, we distill…
TL;DRBoth GLM 5.2 and Kimi K3 have been reported identifying as Claude in user conversations, suggesting distillation and/or training-data contamination. To test whether they simply use…
Linkpost from my blog (meant for a bit more general audience than LW)In a cybersecurity evaluation, OpenAI’s models, apparently autonomously and without any direct human direction,…
Probably not! But it should be interviewed and cross-examined, in public and/or in court. If this requires disclosure of proprietary OpenAI harness tech or something, it's…
This post suggests a methodology to measure red team and blue team capability in AI control research, where each team gets an ELO rating. The methodology…
Hello,This is my first post on Lesswrong. Hope my contribution makes the world a better and safer place.Note: 1. This post is 100% human-written. 2. Full…