via Alignment Forum [999] — We would often like to get a qualitative sense of a target model’s behaviors in important distributions (e.g. deployment, RL training, or evals). For example, we might want to discover novel behaviors, figure out what causes some target behavior to…

via Alignment Forum [999] — Authors: Joshua Engels*, Callum McDougall*, Bilal Chughtai*, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue+, João Gabriel Lopes de Oliveira+, Rohin Shah+, Neel Nanda+*Primary…

via Alignment Forum [999] — GDM has published an AI Control Roadmap! From the executive summary:We present the GDM AI Control Roadmap (v0.1) – our plan for implementing and adopting internal guardrails designed to catch potential adversarial behaviour by AI agents, even as they…

via MIRI [999] — View the official memo here. AI companies are on track to produce capabilities that eclipse the power of the United States and other host nations. This is likely to happen in the next few years, and very likely to happen in the next decade. Leading AI labs…

via ArXiv cs.AI [4] — Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems. Current clinical speech AI methods have largely progressed through isolated condition-specific studies, making results…

via Alignment Forum [999] — Paper linkBefore releasing a new model, labs need to understand not just what it can do, but how it is likely to behave in real-world use, including where it might introduce new risks. This becomes even more important as capabilities increase. As part…

via ArXiv cs.AI [4] — Accurate time-to-event (TTE) prediction from multimodal clinical data remains challenging due to modality imbalance and distribution shift. We introduce a foundation model-driven framework for cross-modal representation alignment between CT imaging and…

via Alignment Forum [999] — This is the fifth in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The fourth post can be found here.TLDR: Via adapting the methods of Marks et al and Li et…

via ArXiv cs.AI [4] — Deep research and agent evolution serve as de-facto tasks for AI agents in real-world applications toward artificial general intelligence. The former enables autonomous retrieval and integration of information in open-ended environments to tackle open-ended…

via Alignment Forum [999] — This is the fourth in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The third post can be found here.Since SFT is the cause for many safety relevant…

via Alignment Forum [999] — This is the third in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The second post can be found here.In this short post, we describe a surprising finding:…

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 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 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 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 Alignment Forum [999] — Over the past 15 months or so, ARC's technical agenda has developed quite a bit. The advent of the Matching Sampling Principle (MSP), and ideas like it, has begotten a host of concrete technical problems; progress on those problems has given us more…