Starting October 9, Gemini app free users are limited to Flash-Lite (no Flash or Pro), and AI Plus ($4.99) keeps Flash-Lite and Flash but loses Pro. AI Pro and Ultra keep all models; Pro also gains Deep Think, and the app is adding low/medium/high effort levels.
Oh My Pi 18.6.1 (Oct 4) fixes native OpenAI compaction rejecting sessions with many screenshots, preserves DeepSeek reasoning for warm Responses sessions and incomplete DSML wrappers, and makes subagent follow ups waitable/cancellable background jobs delivered once…
Google Antigravity now lists Claude Opus 5.5 and Sonnet 5.5 (thinking) for Google AI Pro (non trial) and Ultra only—free, Plus, and Enterprise get none. Claude Sonnet/Opus 4.6 and GPT OSS 120B are marked for removal on Nov 2, 2026…
OpenAI’s Oct 4 prerelease routes eligible remote control launches through the managed daemon, falls back to mklink when Windows daemon junction updates are denied, preserves review lifecycle order on failure, and honors server reasoning summary defaults in new TUI threads. Pin @openai/[email protected] alpha.13 ; npm latest is still 0.160.0…
NVIDIA’s Apache 2.0 SkillSpector checks Claude Code, Codex, and Gemini skills (plus MCP) for prompt injection, exfil, supply chain, and tool poisoning risks—71 patterns across 17 categories, with optional LLM analysis and an MCP scan skill install gate. A 31k skill study found 26.1% vulnerable; install via uv tool install 'skillspector[mcp] @ git+https://github.com/NVIDIA/skillspector.git'…
OpenAI’s Oct 4 prerelease keeps command/patch tools advertised when execution environments are starting or failed (model told to wait), tightens MCP approval routing so unrelated threads can’t surface prompts, and hardens Windows socket ACLs plus managed daemon install retries. Pin @openai/[email protected] alpha.12 ; npm latest is still 0.160.0…
Spotted something we missed? Start a thread.