Claim◆Article · 55 words
Posing the exact same game-building prompt to Codex Desktop running GPT-5.6 Sol Ultra produced a much better game than Claude Fable 5 did.
Author · Simon Willison's Weblog
ExampleArticle · 6:12 — 7:30
Asking both Opus 5 and GPT-5.6 Sol 'who's smarter, you or me?' reveals meaningful differences in their personality and self-perception.
The reviewer posed the same meta-question to both Opus 5 and GPT-5.6 Sol, using their answers as a window into each model's personality traits. ✦ AI generated
Claire Vo · Lenny's Newsletter · 2026-07-24 · original ↗
What I learned from asking both Opus 5 and GPT‑5.6 Sol 'who's smarter, you or me?'
Read full article ↗excerpt · fair-use quotation
Related moments
Claim◆Audio · 3:13 · 2m
Machado de Assis is the Pelé of literature: he inherited a European tradition, mastered it, and transformed it into something unmistakably Brazilian and original.
Viviani Carvalho da Annunciation · In Our Time
Mechanism◆Article · 97 words
The gameplay design of the GPT-5.6 Sol version is dramatically more aligned with the original heist concept than Fable's was.
Author · Simon Willison's Weblog