Traveling dev slams Claude's permission churn and premature session compaction
maier_ak · x · 2026-09-10
User @maierak reports that Anthropic's security harnesses and frequent updates are painful on the road: permissions keep changing, sessions get compacted well before hitting context limits, and the app surfaces none of it — leaving him stuck in a remote session he can't fix. A concrete account of Claude Code's remote/mobile stability issues.
Related event: Developer Paying €20k a Year Says Claude Is Getting Weaker(3 posts)→
More from coding & agent
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27