8 min read
Claude Fable 5.1 Refuses Less: What Actually Changed
Fable 5.1 cuts wrong refusals 85 percent in biology, 60 percent in cyber. Plus the refusal that returns…
The Lab · Written in the open · Tagged Anthropic
Working notes from the studio. The tools I build, the workflows I keep, the mistakes I paid for.
48 entries · latest 2026-09-02
Latest entry
Anthropic shipped Fable 5.1 and Mythos 5.1 on September 1. Here is what actually changes for Claude Code users this week, not just the spec sheet.
Read the entry
Latest entry · AI Tools
All entries · Anthropic
8 min read
Fable 5.1 cuts wrong refusals 85 percent in biology, 60 percent in cyber. Plus the refusal that returns…
8 min read
Fable 5.1 costs double what Opus 5 does. On single questions they are within 1.4 points; on long…
8 min read
All nine Claude Fable 5.1 benchmarks against Fable 5, Opus 5 and GPT-5.6 Sol, plus the 75 percent…
9 min read
A federal judge ruled the Pentagon's Anthropic blacklist was illegal retaliation, and what the case means for a…
8 min read
Anthropic disabled Claude Fable 5 and Mythos 5 on June 12 under a US export order over a…
8 min read
Fable 5 costs 10 dollars per million input tokens against 5 for Opus 4.8, output is 50 vs…
8 min read
Anthropic released Claude Fable 5 on June 9, 2026, the first Mythos-class model anyone can use
9 min read
Migrated 4 of 7 Notion automations to an MCP server in one weekend
10 min read
Retry storms turned 1 timeout into 340 duplicate calls billed in 90 seconds
10 min read
1M context costs full price on every query, caching cuts repeated tokens to 1/10
10 min read
Files API replaced my 40KB inline blobs with reusable file IDs across requests