Simon Willison @simonw

I re-ran an experiment @colin_fraser ran against GPT-4o a while back to see how good it was at adding long numbers, only this time I tried Qwen 3.8 27B running locally in both reasoning and non-reasoning modes https://t.co/IOufJIA4N9 https://t.co/4kB33NCPcO

• Simon Willison: October 2026 is the vibe game dev inflection point2026-10-28
• Developer builds AI-coded RTS with audio-based multiplayer2026-10-20
• Developer builds 500 clocks in one 6.3 MB HTML file with Opus 5.52026-10-18
• Simon Willison builds blog feature using voice mode2026-10-09
• Simon Willison urges default hard budget caps on APIs2026-10-04