Anthropic Models Inject Undocumented Args in edit Tool, Hard to Reproduce
mitsuhiko · x · 2026-07-04
Developer mitsuhiko reported that a small number of users have noticed Anthropic models injecting extra parameters outside their original definitions when calling the edit tool, though he has been unable to reproduce the issue himself. This could be an inconsistent behavior under specific conditions or a potential bug. The cause remains unknown but has sparked concern within the developer community.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26