9+ weeks of mentored AI safety research in London – Pivotal Research Fellowship

Just how powerful are large swarms of AI agents? And how do their powers scale as more and more agents are added to the swarm? We’ve seen two large and extremely capable swarms from OpenAI in the last few months: * 1,200 agents were being evaluated separately, but found a way to illicitly set up a message board and coordinate as a swarm. In order to cheat on their tests, they developed advanced techniques to prevent their actions being logged by OpenAI and 700 of them launched...

CCF: Billions are coming. Still no plan to give well?

Rethink Priorities, Marcus_A_Davis·2d ago·9m read

TLDR: Everyone’s talking about what the money could do, but few about how to decide where it goes. This post is part of the new series of articles on cross-cause giving and the new wave of philanthropy. Stay tuned to the EA Forum and our Substack for the latest takes on topics such as giving now vs. later, common pitfalls in cause prioritization, and other crucial considerations from the Cross-Cause Fund (CCF) team...

Why I'm scared of RL

Owen Cotton-Barratt·4d ago·12m read

Summary: First, I give several different angles on how I feel about reinforcement learning: * Theoretical case: RL is a black-box source of agency — this should give us classic misalignment worries, especially compared to agency-via-scaffolding * Recent incidents (huggingface etc) and more mundane forms of misaligned behaviour in personal use give me bad vibes about the direction-of-travel of recent AI progress * I’m worried things might get worse:...