Anthropic Locks Reasoning in Fable 5.1: Mid-Conv Edits Now Blocked
mitsuhiko · x · 2026-09-02
Anthropic introduced "Preserved Thinking" in Fable 5.1, significantly impacting developer integrations:
Core Restriction
- Modifying conversation history (system prompts, tools, or early messages) mid-conversation is blocked by default.
- API will error unless prefixmismatchbehavior: "dropblock" is set to drop affected thinking blocks.
Rationale
- Uses signatures to verify prior context is unchanged, preventing reasoning replay under adversarial instructions.
- Maintains prefix stability for prompt caching.
Impact & Migration
- Default enforcement starts for new orgs created after Aug 31, 2026.
- Anthropic recommends migrating to native features like mid-conversation system messages instead of editing history.
More from Infra
- SGLang Summit sponsors grow from 11 to 36 in one week; Lip-Bu Tan, Lilian Weng to speak — BanghuaZ · 2026-10-18
- Yacine jokes his datacenter KPI is gigawatt-hours: get paged if not burning enough power — yacineMTB · 2026-10-18
- 1.68x inference speedup drops, directly accelerating GRPO post-training — yacineMTB · 2026-10-18
- OpenRouter is only a fraction of the total addressable market, poster argues — sloppenheimer · 2026-10-18
- Developer builds change alerts for LLM prices and retirements across Bedrock, Azure and Vertex — jsandhu0780 · 2026-10-18
- 12.3M tokens in 27 minutes for $0.14: agent session with 99.6% cache hit — teortaxesTex · 2026-10-18