Gemini 4 Neon called best everyday coding model, beating Opus 5.5
inductionheads · x · 2026-11-19
Blogger aicodeking apologizes to DeepMind: Gemini 4 Neon is now his best everyday coding model, preferred over Opus 5.5, with interesting hidden capabilities. His workflow — Carbon as reviewer, Neon as worker — outperforms Opus 5.5 + Fable 5.2. He also wishes Antigravity would lift its 5-hour limits for long-horizon tasks.
More from coding & agent
- Merge's Agent Handler adds credential passthrough: run tools without storing user tokens — shensi · 2026-11-19
- LangChain raises $300M at $3B valuation and open-sources its design agent — BraceSproul · 2026-11-19
- Volcano, from the Kong team, auto-detects production bugs and opens fix PRs — cneuralnetwork · 2026-11-19
- Mozilla quietly ran Claude over Firefox's 10M-line codebase, fixing 400+ security bugs — claudeai · 2026-11-19
- Researcher's AI workflow advice: start small, do key steps manually before offloading — jmschreiber91 · 2026-11-19
- Open-source akyn-sdk turns any data source into an MCP server in 5 minutes — adnan_hashmi · 2026-11-19