Fable 5.2 effort levels: API defaults to high, xhigh reserved for long-running agentic work
ClaudeDevs · x · 2026-11-10
Anthropic detailed effort defaults for Fable 5.2: high on the Claude Platform (API), medium in Claude apps. xhigh is recommended only for the hardest long-running agentic tasks with measurable gains; max is for probing the ceiling and not for everyday use.
Related event: Anthropic Releases Claude Fable 5.2 and Mythos 5.2(29 posts)→
More from coding & agent
- Claude Fable 5.2 tops FrontierCode 2.0 at 49.1, at a third of Fable 5.1's cost — nrehiew_ · 2026-11-10
- Victor Sanh: overfitting to users is the job when building vertical agents — VictorSanh · 2026-11-10
- Anthropic: Claude Fable 5.2 designs working electronic hardware end to end — EricBuess · 2026-11-10
- Anthropic's 1,000 agents built their own database tables and split into subteams to work in parallel — RLanceMartin · 2026-11-10
- Hardest Fermat lemma spawned a 2,418-task tree across ~750 agents, 10 levels deep — RLanceMartin · 2026-11-10
- Fable 5.2 builds a playable voxel engine from a single prompt — mattshumer_ · 2026-11-10