PredictionArticle

Third-party coding harnesses like Pi may need to implement multiple edit tools so they can use whichever one performs best for the specific underlying model the user has selected.

The piece closes by floating the idea that tools like Pi might need to hedge against model-specific quirks by offering several edit-tool implementations, picking whichever suits the chosen model best. ✦ AI generated

Simon Willison · Simon Willison's Weblog · 2026-07-04 · original ↗

Export .md Export .txt

Does this mean third-party coding harnesses like Pi should implement multiple edit tools just so they can use the one with the best performance for the underlying model the user has selected?

Read full article ↗excerpt · fair-use quotation

✳ Pi

Around this claim

Context · 1

Claude's edit tool is built around search-and-replace, whereas OpenAI's Codex uses an apply_patch mechanism instead, and OpenAI has publicly discussed training its models specifically to use that apply_patch tool well.Simon Willison · Simon Willison's Weblog · conf 60%

This moment responds to

extends → Newer Claude models — including the flagship Opus 4.8, not just small models — sometimes call Pi's edit tool with extra, invented fields in the nested edits[] array, so the arguments fail to match the schema and Pi rejects the tool call and asks for a retry.Armin Ronacher · Simon Willison's Weblog extends → Newer Anthropic models have been specifically trained, presumably via reinforcement learning, to better use the edit tools baked into Claude Code, and this makes them more likely to misuse the differently-shaped custom edit tools of other coding harnesses like Pi.Armin Ronacher · Simon Willison's Weblog