Redwood Research Blog
Blog · Research & Policy · blog.redwoodresearch.org
Research on catastrophic AI risks and ways to reduce them.
Summary written from the source’s own About page · checked 2026-11-21
Latest Posts
Titles link to the original on blog.redwoodresearch.org. We never copy article text.
- How should we define “capabilities activities” for the purpose of pacing?Nov 17 21:36 UTC
- Gemini 4 safety reports don’t demonstrate low loss-of-control riskNov 16 17:21 UTC
- We don’t understand whether GDM intentionally trains on CoTNov 10 20:23 UTC
- Astra covertly underperforming on safety research is concerning, even though it’s unlikely to be motivated by ambitious goalsNov 9 17:33 UTC
- OpenAI agents keep disabling monitoring; is this being handled appropriately?Nov 4 06:34 UTC
Publishing Activity
Posts per week over the last 12 weeks, from its feed
Similar Sources
Same main topic: Research
- Papers
arXiv cs.LG
New preprints in machine learning on arXiv.
Posts daily - News site
MarkTechPost
AI news platform covering new models and research papers.
Posts daily - Lab Blog
Google Research Blog
The latest research from Google.
- News site
MIT News: Artificial Intelligence
MIT News stories about artificial intelligence research at MIT.
Posts daily
How these numbers are made: we read this source’s public feed every 6 hours. Posting rate, last post, topic mix and “first to report” come from that feed and from how we group stories across all sources. We never show ratings or reviews. Read the methodology →