한국어EN
Safety, Alignment & InterpretabilityAnthropic

Petri

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

Petri — an open-source automated auditing tool

Why it matters

Safety evaluation moves from manual red-teaming to agent pipelines

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

Officialanthropic.comhttps://www.anthropic.com/research/petri-open-source-auditing

Added in Week 35, 2026 · See that week

On the map — ⑩ Safety, Alignment line

  1. Previous stopAnthropic classifiers
  2. This record · stopPetri
  3. Next stopClaude Opus 4.6
See it on the map

Same week

Claude Code plugins enter public betaOfficialFigure unveils Figure 03OfficialGemini 2.5 Computer UseOfficialApps SDKOfficial

Nearby on the same axis

Frontier Safety Framework v3.0OfficialOpenAI and Apollo Research stress-test anti-scheming trainingPaperxAI launches Grokipedia v0.1 (800,000+ articles)PressEmergent Introspective AwarenessOfficial