ATRIUMsearch → argument graph
AnecdoteArticle

When given an open-ended review prompt, Claude Fable 5 wrote 12 scratch scripts and found 4 release blockers plus 10 additional issues, far outperforming GPT-5.5 xhigh in Codex Desktop, which wrote only 5 scripts and found nothing particularly interesting.

Given the same open-ended pre-release review task, Claude Fable 5 dramatically outperformed GPT-5.5, surfacing 14 real issues (including transaction and foreign-key bugs) via self-written repro scripts, versus GPT-5.5 finding nothing notable. ✦ AI generated

Simon Willison · Simon Willison's Weblog · 2026-07-07 · original ↗

Fable 5 wrote 12 scripts, identified 4 release blockers and 10 additional issues in its report, and built a neat combined repro script... I found myself agreeing with almost all of them. Here's the PR with 16 commits where we worked through them in turn.

Read full article ↗excerpt · fair-use quotation

Around this claim