Dev: Gemini's G-Suite tools broke while Claude Code and Codex got more reliable
3scorciav · x · 2026-11-03
The author shares hands-on experience: they used to enjoy Gemini's G-Suite integration, especially the YouTube tool, but it stopped working properly earlier this year. Meanwhile Claude Code (Skills) and OpenAI Codex (Plugins, browser use) became more reliable.
They further question Google: Googlers may not be lying, but "our model is awesome — pay to find out" feels elitist when others ship good stuff in freemium. Why can't a company with massive compute and distribution do better — a PM problem or a deeper organizational issue?
More from coding & agent
- 'Opus 5.5 refactored my codebase into a Grosse Fuge — my team hates it, history won't' — eigenron · 2026-11-03
- Scale AI's READY framework: identical-accuracy agents need 39.2% vs 29.6% human review — demian_ai · 2026-11-03
- GitHub Copilot team publishes first-party data on which models perform best — unixterminal · 2026-11-03
- Benchmarking System 1 decision models: 40 yes/no questions in one pass, 159ms agent routing — ThatOneSnare · 2026-11-03
- Browser agents rarely fail at reasoning — modals, focus rendering and silent save failures break them — yantra-lucy02 · 2026-11-03
- Zed CEO shares weekly agent changelog automation summarizing 250 commits — zeeg · 2026-11-03