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
- Reticle builds a verification layer that lets AI coding agents check their own generated code — Scobleizer · 2026-10-27
- Trust your agent, but read its logs: Claude managed agents tips — brada · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- Dev trains a ~4GB-VRAM sentinel model to guard against prompt injection and poisoned memory — gnukeith · 2026-10-27
- Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Ex-Big Tech managers may thrive in the AI era: manage agents like you managed teams — lxfater · 2026-10-27