via LessWrong AI [4] — TL;DR: vLLM-Lens is a vLLM plugin for top-down interpretability techniques[1] such as probes, steering, and activation oracles. We benchmarked it as 8–44× faster than existing alternatives for single-GPU use, though we note a planned version of nnsight…

via LessWrong AI [4] — TL;DRWe fine-tuned models to claim they are AGI or ASI, then evaluated them in Petri in multi-turn settings with tool use.On GPT-4.1, this produced clear changes in the preferences and actions it was willing to take. In the most striking case, the…

via LessWrong AI [19] — tl;dr: Lens Academy offers a new course introducing ASI x-risk for AI safety newcomers, centered around the book IABIED. We share our hypothesis of why IABIED seems more appreciated by AI Safety newbies than by AI Safety insiders.Lens Academy's new intro…

via LessWrong AI [4] — Claude really got me lately.I’d given it an elaborate prompt in an attempt to summon an AGI-level answer to my third-grade level question. Embarrassingly, it included the phrase, “this work might be reviewed by probability theorists, who are very…

via Substack Zvi [999] — This was the week of Claude Opus 4.7.

via Substack Zvi [999] — It is thanks to Anthropic that we get to have this discussion in the first place.

via Substack Zvi [999] — Claude Opus 4.7 raises a lot of key model welfare related concerns.

via Substack Zvi [999] — Less than a week after completing coverage of Claude Mythos, here we are again as Anthropic gives us Claude Opus 4.7.

via LessWrong AI [5] — It seems that AI safety is at least partly bottlenecked by a lack of orgs. To help address that, we’ve added a page to AISafety.com aimed at lowering the friction for starting one: AISafety.com/founders.This page was built largely as the result of a…

via LessWrong AI [7] — 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…

via LessWrong AI [5] — AKA scalable oversight of value driftTL;DR LLMs could be aligned but then corrupted through RL, instrumentally converging on deep consequentialism. If LLMs are sufficiently aligned and can properly oversee their training updates, we they can prevent…

via Substack Zvi [999] — This is a day late because, given the discourse around Dwarkesh Patel’s interview with Jensen Huang, I pushed the weekly to Friday.

via Substack Zvi [999] — Some podcasts are self-recommending on the ‘yep, I’m going to be breaking this one down’ level.

via LessWrong AI [9] — Almost two months ago, Iliad announced the Iliad Intensive and Iliad Fellowship. Fellowships are a well-understood unit, but what is an intensive? This post explains this in more detail!Comparison. The Iliad Intensive has similarities to ARENA, but focuses…

via Substack Zvi [999] — As we all try to figure out what Mythos means for us down the line, the world of practical agentic coding continues, with the latest array of upgrades.

via LessWrong AI [4] — How I learned about Deep Learning.As far as I know, I’m the second person ever to get into the field of AI largely because I was worried about the risk of human extinction.1In late 2012, while recovering from some minor heartbreak with the help of some…

via LessWrong AI [8] — Written very quickly for the InkHaven Residency.In 2022, Richard Ngo wrote a list of 26 Conceptual Alignment Research Projects. Now that it’s 2026, I’d like to revisit this list of projects, note which ones have already been done, and give my thoughts on…

via Substack Zvi [999] — To round out coverage of Mythos, today covers capabilities other than cyber, and anything else additional not covered by the first two posts, including new reactions and details.

via LessWrong AI [5] — This post was cross posted to the EA ForumTL;DR: One of the largest talent gaps in AI safety is competent generalists: program managers, fieldbuilders, operators, org leaders, chiefs of staff, founders. Ambitious, competent junior people could develop the…

via Substack Zvi [999] — Nor is the threat or implication of violence.