Google’s internal code still outclasses Gemini on writing quality, says engineer
yunta_tsai · x · 2026-07-24
The author says Google3 has code that taught them a lot about what a strong human programmer can do, but Gemini still did not write code as well.
It is a brief qualitative comparison between human-written internal Google code and Gemini’s coding output, pointing to a gap in code quality rather than a product announcement or workflow tip.
More from Models
- Kimi K3 appears to distill cleanly onto Gemma4 — tokumin · 2026-07-24
- Claude screenshot says it has no original math results, and the reply is pure meme fuel — mimi10v3 · 2026-07-24
- Anthropic is reportedly hiding Fable 5’s reasoning traces — ns123abc · 2026-07-24
- MindLab open-sources Macaron-V1, a GLM-5.2 family built on continual learning — 机器之心 · 2026-07-24
- Unlimited-OCR returns to No. 1 on Hugging Face trending models — _akhaliq · 2026-07-24
- V4 update slips, with K3 weights possibly landing in the same release window — teortaxesTex · 2026-07-24