한국어EN
Safety, Alignment & InterpretabilityGoogle DeepMind

Frontier Safety Framework v3.0

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

Frontier Safety Framework v3.0

Why it matters

Adds harmful manipulation as a new CCL and tackles misalignment, such as resistance to shutdown, head-on

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

Officialdeepmind.googlehttps://deepmind.google/blog/strengthening-our-frontier-safety-framework/

Added in Week 35, 2026 · See that week

On the map — ⑩ Safety, Alignment line

  1. Previous stopAnthropic classifiers
  2. This recordFrontier Safety Framework v3.0
  3. Next stopPetri
See it on the map

Same week

Cloudflare announces Code ModeOfficialSutton rejects the LLM path outright on Dwarkesh PodcastPressGemini Robotics 1.5 and ER 1.5OfficialPreliminary approval of the $1.5 billion Bartz v. Anthropic settlementPress

Nearby on the same axis

OpenAI and Apollo Research stress-test anti-scheming trainingPaperPetriOfficialAnthropic and OpenAI publish a mutual alignment evaluation pilotOfficialxAI publishes its Risk Management FrameworkOfficial