Simon Willison says loops are becoming obsolete as models handle long tasks natively
teropa · x · 2026-07-23
Loops may be becoming unnecessary for long-horizon model work
Simon Willison argues that loops were a short-lived workaround for models that could not reliably keep working on a long task until they reached a defined goal.
He says newer systems like Fable and GPT-5.6 — and probably Kimi K3 too — can already do this out of the box, without needing an external loop or orchestration layer.
Related event: Simon Willison: Native Long-Task Skills Will Outphase AI Loops(3 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11