https://sysnote.net/news/claude-fable-5-2-launch-one-to-three-fable-limit-resets-for-max-and-ultra-a-free sysnoteen 2026-11-09T21:36:00+00:00 Claude Fable 5.2 launch: one to three Fable limit resets for Max and Ultra, a free Fable week for Pro https://sysnote.net/news/claude-fable-5-2-is-cheaper-and-finally-beats-opus-5-5-at-coding-but-the-api-cha sysnoteen 2026-11-09T21:35:55+00:00 Claude Fable 5.2 is cheaper and finally beats Opus 5.5 at coding, but the API change that will break integrations is preserved thinking https://sysnote.net/news/qwen3-8-flash-next-still-invents-alibaba-cloud-urls-two-weeks-after-cohere-s-rep sysnoteen 2026-11-09T20:00:12+00:00 Qwen3.8-Flash-Next still invents Alibaba Cloud URLs two weeks after Cohere's report, and Qwen hasn't said a word https://sysnote.net/news/does-chatgpt-desktop-forward-your-ssh-agent-only-if-your-ssh-config-does-and-the sysnoteen 2026-11-09T13:05:07+00:00 Does ChatGPT Desktop forward your SSH agent? Only if your SSH config does, and then Codex shares it https://sysnote.net/news/is-claude-opus-5-5-nerfed-the-november-3-change-was-the-thinking-summarizer-the sysnoteen 2026-11-09T09:06:12+00:00 Is Claude Opus 5.5 nerfed? The November 3 change was the thinking summarizer; the October 19 step is still unexplained https://sysnote.net/news/postman-reverts-agent-plugin-auto-install-and-drops-its-codex-hook-self-approval sysnoteen 2026-11-09T05:10:21+00:00 Postman reverts agent-plugin auto-install and drops its Codex hook self-approval, but npm's default build still has it https://sysnote.net/news/claude-code-s-don-t-ask-again-saves-passwords-verbatim-1-122-public-files-and-a sysnoteen 2026-11-08T17:27:22+00:00 Claude Code's "don't ask again" saves passwords verbatim: 1,122 public files and a bug a bot closed in January https://sysnote.net/news/maxxbench-mutating-deepswe-tasks-by-a-median-17-lines-separates-models-that-all sysnoteen 2026-11-08T12:58:59+00:00 MaxxBench: mutating DeepSWE tasks by a median 17 lines separates models that all scored about 74% https://sysnote.net/news/openai-s-tibo-confirms-codex-pro-usage-no-5-hour-limits-and-10x-20x-and-50x-plus sysnoteen 2026-11-08T12:58:52+00:00 OpenAI's Tibo confirms Codex Pro usage: no 5-hour limits, and 10x, 20x and 50x Plus on Pro 100, 200 and 500