Newsletter September 6, 2026
How this is created. 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
- Claude OAuth mimic uses an outdated Claude Code fingerprint
It is a GitHub project that uses an OAuth imitation for Claude with an outdated Claude Code fingerprint, which is relevant for indie developers needing reliable authentication for AI integrations. - Subagent spawn crashes 100% of the time when resolved model provider is google-antigravity (TypeError: rt.getWorkPoolYieldItems)
This is a GitHub issue where starting Subagent crashes every time when using the model provider google‑antigravity, which is important for indie developers who rely on that component.
Models & pricing
- We benchmarked Claude Fable 5.1 and Gemini 3.8 Flash on surgical intelligence: - The performance of the two new releases is spiky (e.g. goo
It is a benchmark of Claude Fable 5.1 and Gemini 3.8 Flash on surgical intelligence, reporting volatile performance, which is relevant for indie developers who want to use these models for critical applications.
Repo's, releases & updates
- GPT-6 Astra Is Here. But Can We Trust the Leaderboards? @OpenAI released GPT-6 Astra, calling it its most capable model yet across coding,
This concerns the announcement of OpenAI’s GPT‑6 Astra and a discussion about the reliability of leaderboards, which is relevant for indie developers considering this model for code generation. - my take on the recent Google situation: release delays + talent exits make more sense if they're shifting toward RSI, autonomous AI, robotic
This is a personal analysis of Google’s recent release delays and staff turnover, suggesting a shift toward RSI, autonomous AI and robotics, which is relevant for indie developers using Google technologies.