Constitutional Classifiers

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Constitutional Classifiers

Why it matters

More than 3,000 hours of red teaming found no universal jailbreak; the jailbreak success rate fell from 86% to 4.4%. The cost was a 23.7% increase in compute

Source — Primary sources first; secondary reports are labelled “Press”

Officialanthropic.comhttps://www.anthropic.com/news/constitutional-classifiers

Added in Week 35, 2026 · See that week

On the map — ⑩ Safety, Alignment line

  1. Previous stopAlignment faking
  2. This record · stopAnthropic classifiers
  3. Next stopPetri
See it on the map

Same week

Modarressi et al. present NoLiMaPaperKarpathy releases Deep Dive into LLMs like ChatGPT, a 3h31m YouTube lectureOfficial

Nearby on the same axis

Monitoring Reasoning Models for MisbehaviorPaperAuditing Language Models for Hidden ObjectivesOfficialDeliberative AlignmentPaperAlignment Faking in LLMsOfficial