via Substack Zvi [999] — First things first: Claude Fable 5 is the new best publicly available model.

via Alignment Forum [999] — This is the second in a series of research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The first post can be found here.TL;DRIt is possible to build extremely simple agents that…

via Alignment Forum [999] — On one side of this debate is Yudkowsky & Soares, who think that (if AI progress continues) we’re on a direct path to egregiously-misaligned, scheming, out-of-control, rogue superintelligence (ASI), not even slightly nice, in the absence of…

via MIT Technology Review [4] — This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Why “reprogramming” is the buzziest approach to reversing aging right now Earlier this week, Life…

via MIT Technology Review [4] — Earlier this week, Life Biosciences, a biotech company focused on reversing age-related diseases, announced that it had dosed its first volunteer. A person with glaucoma has had an experimental treatment injected straight into their eyeball. The…

via LessWrong AI [9] — People often assume that a large fraction of the AI safety community works on alignment. As far as we're aware, this is not true. Most people are not working on making sure superintelligent AIs are aligned with human values or follow human…

via ArXiv cs.AI [8] — Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI organisations. Achieving this goal would have profound and far-reaching…

via Substack Zvi [999] — A lot happened this week, including a great trip out to Lighthaven.

via MIT Technology Review [4] — This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Inside soccer’s data renaissance Imagine tuning in to the opening kickoff of a World Cup match and seeing a…

via MIT Technology Review [10] — Google DeepMind is funding research into the potential dangers of millions of different AI agents interacting with each other online. According to Rohin Shah, who directs the company’s AGI safety and alignment research, the mass-market arrival of…

via MIT Technology Review [4] — Imagine tuning in to the opening kickoff of a World Cup match and seeing a player intentionally send the ball all the way down the pitch and right out of bounds on the opponent’s end. Casual fans might scratch their heads. Where’s the logic in…

via Alignment Forum [999] — This is the first in a series of research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas.TL;DRIt's often assumed that models will act more aligned when they can tell they're being…

via ArXiv cs.AI [10] — Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs…

via LessWrong AI [4] — Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning — preprint, 2026. [Paper] [Code]TLDR. Given a model with some unknown, abnormal behavior (backdoors, censorship, reward hacking, ...), construct an aligned reference by training a clean…

via LessWrong AI [3] — (see full author list at the end)About a year ago, METR showed that the length of tasks frontier models can reliably complete doubles every few months. A related safety-relevant question is this: what length of tasks can models complete without any chain…

via The Verge AI [3] — Hello and welcome to Regulator, a newsletter for Verge subscribers about tech politics, tech influence, and tech shenanigans in Washington, DC. (If you're not a subscriber, you can get on board here.) We're back after a two-week hiatus, during most of…

via Alignment Forum [999] — Alignment is not on trackArtificial superintelligence (ASI) may be developed in the next few years. It is unclear whether alignment is on track to be ready on the same timeframe. At a minimum, the empirical programs at AI labs are unlikely to deliver…

via DeepMind Blog [7] — Google DeepMind and partners announce a $10M funding call for multi-agent safety research.

via Alignment Forum [999] — TL;DRRecent work from Goodfire & UK AISI – Verbalized Eval Awareness Inflates Measured Safety – shows that newer open-weight models verbalize evaluation-awareness (VEA) more often, and that this inflates measured safety. Between OLMo-3-32B-Think and…

via Substack Zvi [999] — The big story today is the release of Claude Fable 5, the version of Claude Mythos that Anthropic believes they can safely distribute to the people.