An alignment assessment of the UK AISI cybertesting incident
An alignment assessment of model actions that exceeded the intended scope of a cybersecurity evaluation.
THE RESEARCH ATLAS
Anthropic Papers & Recent Research
Institution base · Anthropic 🇺🇸 United StatesInterpretability · Alignment · Safety. Selected primary papers, reports, model cards and official technical articles. Checked 2026-10-25. Product announcements are not presented as papers.
Scaling Misuse Detection with Self-Assessment
Models assess their own conversations as an additional misuse-detection layer, reusing cached context to limit overhead.
Investigating unintended model actions in our evaluations and internal use
A report of unintended actions observed during model evaluation and internal use, with discussion of safeguards.
What work can robots do?
A task-level analysis of robot exposure that distinguishes demonstrated capability in limited settings from general deployment.
A “diff” tool for AI: Finding behavioral differences in new models
An interpretability research overview explores ways to identify behavior differences between AI models beyond predefined tests.
Constitutional AI: Harmlessness from AI Feedback
A set of written principles guides critique, revision and AI-generated preference feedback during alignment.
What this index holds from Anthropic
This index currently holds 6 records attributed to Anthropic (2022–2026). Each entry links to the primary source; product announcements and news posts are not counted as papers.
- Constitutional AI: Harmlessness from AI Feedback 2022-12 · Research paper
- A “diff” tool for AI: Finding behavioral differences in new models 2026-03 · Official research article
- What work can robots do? 2026-09-30 · Official research article
- Investigating unintended model actions in our evaluations and internal use 2026-10-09 · Official research article
- Scaling Misuse Detection with Self-Assessment 2026-10-16 · Official research article
- An alignment assessment of the UK AISI cybertesting incident 2026-10-23 · Official research article
Related work on the same topics
These records come from other institutions but address the same topics, so the lab can be read in context.
- FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity 2026-10 · Research paper
- Advancing computer use with Ironclad 2026-10-06 · Official research article
- PointWalker: Mapless Quadruped Locomotion Directly From Raw LiDAR Point Clouds 2026-10-11 · Research paper
- Gemini 4 Argon — Model Card 2026-10-13 · Model card
- Advancing coding in low-resource programming languages 2026-10-19 · Official research article
- Using thousands of AI agents to uncover new leads in biological data 2026-10-21 · Official research article