Coding Agents Changed My Output Curve
Simon Willison · rss · 2026-07-14
Simon Willison used the GitHub code-frequency graph of his project, Datasette, to observe the impact of coding agents and Opus 4.5-level models on his personal output.
He discovered a significant spike in code commits at the end of the chart, which aligns perfectly with the release timelines of Opus 4.8, GPT-5.5, Fable 5, and GPT-5.6 Sol.
Rather than focusing on a single tool, the post highlights how the pace of code changes in personal open-source projects has been fundamentally altered by new models in the era of coding agents.
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26