Opus 5 is a really bad model
- Source
- はるか
- Author
- はるか
- Date
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
A practitioner's log of specific Opus 5 regressions — silently dropping injected CLAUDE.md/rule files and editing files without reading them first — that explains why setups tuned for earlier models suddenly misbehave and what to force explicitly.
“After trying out Opus 5 for a few hours today, I honestly think Anthropic's benchmark scores are a complete fraud.”
“Sure, the model might have improved in a few areas, but it has regressed unbelievably on so many weird, basic things.”
“It regularly skips reading files, running ls, or running grep, and just hallucinates what the working directory looks like.”
“Even when the model reads a file, its responses and comprehension make it feel like it only skimmed grep snippets instead of reading the whole document.”
“As a result, the long-running task persistence that Claude Code was once proud of is completely ruined.”
Checking sign-in…
Loading comments…