Mitsuhiko: Claude Code struggles with transcripts and needs a read tool for images
mitsuhiko · x · 2026-09-22
Armin Ronacher discusses practical issues feeding transcripts to Claude Code: you first need a read tool for images, and results are mixed with more tool-call/edit failures. Most importantly, on new SOTA models you can't read the full transcript anymore. He notes Claude Code already synthesizes edit views in the transcript from git diffs.
Related event: mitsuhiko's bash-only Benchmark Yields Mixed Results(2 posts)→
More from coding & agent
- Disaster relief team runs OpenClaw multi-agent system across 8 messaging channels — heyneighbor · 2026-09-22
- Auto-Optimizing a Non-LLM to Read Chinese Halves Errors at 1/7 the Cost of DeepSeek — davernow · 2026-09-22
- jev-gc: A Context Garbage Collector for LLM Agents, Built With Claude — Maleficent_College57 · 2026-09-22
- Dev complains openclaw is a permissions nightmare, unsure if setup or the tool — brianmichel · 2026-09-22
- Codex code leak reveals Aeon, OpenAI's rumored persistent agent, launch may be imminent — ChrisGPT · 2026-09-22
- Engineer autonomously trains a Jev-competitive model with an agent swarm for $3.1k in 20 hours — denisyarats · 2026-09-22