To test the broader usefulness of the AARs’ methods, we assessed how well they worked on two datasets the AARs hadn’t seen before. The AARs’ best-performing method successfully generalized to both coding and math tasks, though their second-best method only generalized to math.
@anthropicai
-
Automated Alignment Researchers Surpass Human Performance by 97%
By
–
Here, we measure success by the fraction of the “performance gap” we can close between the weak model and the potential of the strong model. After 7 days, human researchers closed it by 23%. Then, our Automated Alignment Researchers—Opus 4.6 with extra tools—closed it by 97%.
-
Anthropic Develops Automated Alignment Researcher with Claude
By
–
New Anthropic Fellows research: developing an Automated Alignment Researcher. We ran an experiment to learn whether Claude Opus 4.6 could accelerate research on a key alignment problem: using a weak AI model to supervise the training of a stronger one.
-
Vas Narasimhan Joins Anthropic Board of Directors
By
–
Our Long-Term Benefit Trust has appointed Vas Narasimhan to Anthropic's Board of Directors. Vas brings more than two decades of experience in medicine and global health, including as CEO of Novartis. Read more:
-
Anthropic Launches Managed Agents for Unpredictable Programs
By
–
New on the Engineering Blog: Building Managed Agents—our hosted service for long-running agents—meant solving an old problem in computing: how to design a system for "programs as yet unthought of." Read more: anthropic.com/engineering/managed-agents [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-08 17:20 UTC
-
Claude Mythos Preview System Card Now Available
By
–
The Claude Mythos Preview system card is available here: anthropic.com/claude-mythos-preview-system-card [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-07 18:15 UTC
-
Technical Report on Vulnerabilities Discovered by Claude Mythos
By
–
You can read a detailed technical report on the software vulnerabilities and exploits discovered by Claude Mythos Preview here: https://red.anthropic.com/2026/mythos-preview [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-07 18:06 UTC
-
Anthropic Invests 100M$ in Mythos Credits for Partners
By
–
We're committing up to $100M in Mythos Preview usage credits for our partners and over 40 other organizations that maintain critical software, including open-source projects. Anthropus will report back what we learn. [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-07 18:06 UTC
-
Anthropic Won’t Release Mythos Preview Publicly, Tests Safeguards
By
–
We do not plan to make Mythos Preview generally available. Our goal is to deploy Mythos-class models safely at scale, but first we need safeguards that reliably block their most dangerous outputs. We'll begin testing those safeguards with an upcoming Claude Opus model. [Translated from EN to English]
→ View original post on X — @anthropicai, 2026-04-07 18:06 UTC
-
AI Progress Accelerating: Optimism for Defensive Applications
By
–
Given the pace of AI progress, it won't be long before models this capable are widespread. But there are strong reasons for optimism: AI will also be invaluable for defensive work.
→ View original post on X — @anthropicai, 2026-04-07 18:06 UTC