Claude Opus 5 works okay only if you set autocompact to 200k tokens, dev reports
bclavie · x · 2026-08-26
@bclavie shares hands-on notes on Claude Opus 5: still quite limited and requiring much more deliberate prompting, but relatively workable if you set autocompact to 200k tokens. Beyond that, it feels context-rotted to an extent even early-2025 models wouldn't hit.
More from coding & agent
- Developer Builds Unified Workspace to Debug Multi-Agent LLM Swarms — Impressive-Iron5216 · 2026-08-26
- Sentry founder recommends Cloud or CLI for agent integrations, new release coming — zeeg · 2026-08-26
- Inventory Blindness: Why AI Agents Forget the Skills They Already Have — TechPreacher · 2026-08-26
- Fable struggles with ripgrep flags, adding erroneous -r unlike Codex — andersonbcdefg · 2026-08-26
- Zero-dependency Python tool resolves relative links and inlines images as base64 for multimodal LLMs — Mediocre-Ease4060 · 2026-08-26
- Agent Memory Benchmark Exam Released for First-Person Contexts — LowDistribution3995 · 2026-08-26