Latest

Every published item, in order · 90 items
Sep 28
Sep 27
Sep 26
Sep 25
Sep 24
Sep 23
How-toBuildersMulti-sourceSelected14:48
Anthropic Releases Prompt and Harness Adjustments for Claude Opus 5.5

The practical takeaway is that effort settings do not transfer across models: teams reusing old configurations for Opus 5.5 may overspend or trigger refusals from leftover reasoning-extraction instructions. The checklist-based harness pattern for preventing premature end_turn stops is directly reusable in long-running agent workflows. Developers running unattended coding, audit or migration tasks on the Claude API will get the most value from the guide.

Event
shao__meng@shao__meng11 sourcesSource
How-toBuildersSelected73°01:11
Fable and Opus Loop Cuts Token Costs in Coding Workflows

The loop turns model review into an automated gate, so the expensive model spends tokens on planning and judgement rather than routine execution. Developers on metered Claude plans can replicate it with a single advisor command and one review prompt, cutting manual back-and-forth. The /compact timing tip matters too: compressing right after the plan is written lands while prompt caching is still warm, so it costs less than compacting after the cache expires.

Event
宝玉@dotey2 sourcesSource
Aug 27
Jul 31
Jul 30