~www_lesswrong_com | Bookmarks (703)

Published on February 7, 2025 1:03 AM GMTBeing a newcomer and having your post downvoted can be very discouraging. This isn't necessarily a bad thing—obviously we want to discourage people from posting things that are not worth our time to read—but it doesn't provide much feedback other than "something about this post/comment/question/answer makes it undesirable to have on LessWrong". So here's my idea:If you...

Published on February 6, 2025 11:33 PM GMTSummary AI may produce a windfall surge in government revenues in 5 to 10 years. I want governments to spending a small fraction of that windfall on retroactively rewarding entities in proportion to how they have contributed to medical advances, measured by lives saved and suffering avoided. Motivations This post was inspired in part by Critch: Healthcare,...

Published on February 6, 2025 7:18 PM GMTTL;DR: How do AI systems make moral decisions, and can we influence their ethical judgments? We probe these questions by examining Llama's 70B (3.1 and 3.3) responses to moral dilemmas, using Goodfire API to steer its decision-making process. Our experiments reveal that simply reframing ethical questions - from "harm one to save many" to "let many perish to...

Published on February 6, 2025 6:58 PM GMTOpen Philanthropy is launching a big new Request for Proposals for technical AI safety research, with plans to fund roughly $40M in grants over the next 5 months, and available funding for substantially more depending on application quality. Applications (here) start with a simple 300 word expression of interest and are open until April 15, 2025.OverviewWe're seeking proposals across...

Published on February 6, 2025 6:52 PM GMTWelcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.Listen to the AI Safety Newsletter for free on Spotify or Apple Podcasts.Reasoning ModelsDeepSeek-R1 has been one of the most significant model releases since ChatGPT. After its release, the DeepSeek’s app quickly rose to...

Published on February 6, 2025 4:15 PM GMTCrossposted from my blog which many people are saying you should check out!  Imagine that you came across an injured deer on the road. She was in immense pain, perhaps having been mauled by a bear or seriously injured in some other way. Two things are obvious:If you could greatly help her at small cost, you should do...

Published on February 6, 2025 3:46 PM GMTCan you tell when an LLM is lying from the activations? Are simple methods good enough? We recently published a paper investigating if linear probes detect when Llama is deceptive.Abstract:AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while its internal...