RSP v2.0

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

RSP v2.0

Why it matters

Overhauled the capability-threshold framework

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

Officialanthropic.comhttps://www.anthropic.com/rsp-updates

Added in Week 35, 2026 · See that week

On the map — ⑩ Safety, Alignment line

  1. Previous stopfirst Model Spec
  2. This recordRSP v2.0
  3. Next stopSynthID-Text
See it on the map

Same week

GENIAC cycle 1 yields PLaMo-100B-Pretrained (100B parameters, from scratch)OfficialAnthropic launches prompt improver in the ConsoleOfficial

Nearby on the same axis

Google DeepMind publishes SynthID-Text in NaturePaperSabotage Evaluations for Frontier ModelsPaperAlignment Faking in LLMsOfficialDeliberative AlignmentPaper