Skip to content
Papers.

Anthropic research papers

Company · 4 papers · 4,835 citations · latest Jan 2025

Research page

4 of 4 papers, newest first

PaperCitations
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingClassifiers trained from a written constitution held off universal jailbreaks through more than 3,000 hours of red teaming.Alignment and safety · Jan 2025199
Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Alignment and safety · Dec 2024342
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Alignment and safety · Jan 2024576
Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Alignment and safety · Dec 20223,718
About and links

Topics: Alignment and safety 4

Anthropic on Companies (companies.fru.dev)

Also onAcquisitions·Paydays·Releases·TechConf

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.