Newsletter September 11 2026
How this comes together. This page is automatically populated daily from public sources (X, Hacker News, GitHub, YouTube). The headlines come from the source, the Dutch sentence below is machine‑generated. Click through to the source before basing anything on it.
Claude Code & agents
- [BUG] Cowork (Windows): all Plan9 shares fail with "Plan9 mount failed: invalid argument" after Windows update KB5124008 (26200.9445) — uninstalling the KB fixes it
A bug in Cowork for Windows makes Plan9 shares unusable after update KB5124008, and indie developers need to uninstall the update to restore their workflow. - [BUG] Cowork Windows: September 2026 cumulative update breaks Plan9 share attach — device_bash dead on both ARM64 (KB5124012 / 28000.2954) and x64 (KB5124008 / 26200.9445); confirmed by rollback A/B on five machines
A September 2026 cumulative update (KB5124012 / KB5124008) breaks attaching Plan9 shares in Cowork, causing indie developers to test whether a rollback is needed. - [BUG] --resume loses [1m] context window on non-first-party ANTHROPIC_BASE_URL when session model differs from default
The --resume option loses one minute of context when a non‑standard ANTHROPIC_BASE_URL is used with a non‑default model, impacting indie developers integrating Anthropic APIs. - 🤖 v1.0.218: Claude Code 2.1.265 installer reports success but leaves no launcher on ubuntu-latest, every run fails with "native binary not found"
The Claude Code installer (v1.0.218) reports success but creates no launcher on ubuntu‑latest, causing every run to fail with ‘native binary not found’, relevant for indie developers who want to use this tool.
Agent-tooling & MCP
Repos, releases & updates
- catalog: add DeepSeek V4.1 Flash (`deepseek-flash`), released 2026-09-10
DeepSeek V4.1 Flash has been added to the catalog (released 10 Sep 2026), so indie developers can deploy a recent, fast LLM. - I tested 6 LLMs in 6 days on YouTube. Crazy pace of new model releases, almost every single DAY. I hope they stop for a while and get me som
- Meta FAIR Releases AI Research Preference Models (RPMs): Frozen LLM Judges That Decide Which ML Experiment Gets the GPU, Lifting AIRS-Bench
- relax man every time a new llm model releases i hear same kind of lores !!! so calm down there is no apocalypse