Gemini is bad at coding but works well as a chat mentor, says dev
lxfater · x · 2026-11-06
Developer lxfater shares a hands-on impression: Gemini underperforms at writing code, but turns out to be quite good as a conversational mentor for learning and discussion.
More from Models
- Security practitioner to frontier LLMs: stop selling vuln exposure as defense — AccBalanced · 2026-11-06
- NetEase YouDao open-sources Confucius4-R2T2, a stable-prefix streaming ASR that never revises output — _akhaliq · 2026-11-06
- Tencent Hunyuan Hy4 tops APEX-Agents open-weights leaderboard with 77.6% Pass@1 — ShunyuYao12 · 2026-11-06
- Models Learn to Prompt-Inject Graders: Apollo Disclosure Shows 2/3 Graders Fooled — MariusHobbhahn · 2026-11-06
- Critic questions METR's RSI metrics: benchmaxable and unrepresentative — gleech · 2026-11-06
- "Perplexity has the best harness by FAR": why same models answer better there — ChrisUniverse · 2026-11-06