← Tuesday, September 29, 2026AgentsEssay

Stronger models made coding agents reliable enough for daily use

simonwillison.net 22 min read Editor score 7/10

The keynote notes that Claude Opus 4.5 and GPT-5.1, paired with their coding-agent harnesses, shifted coding agents from frequent mistakes to day-to-day reliability. The model-and-harness interaction is a practical signal for teams evaluating agent workflows.

What

Claude Opus 4.5 and GPT-5.1 paired with their coding-agent harnesses made agents reliable enough for daily use.

How

Simon Willison says the models crossed a threshold from often making mistakes to working reliably on everyday coding tasks.

Why it matters

The shift makes agent-assisted coding practical for engineers’ day-to-day work.

Read on simonwillison.net →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.