Indie researcher: Gemini products lag badly for large agent swarms, when's the new Gemma?
npinto · x · 2026-10-30
After banter with a Googler, npinto gives a straight answer: he has tried Antigravity. He likes the Gemma line (asking when a new revision ships), but finds Gemini's models and especially products (Gemini apps, agy cli) far behind when scaling to large p2p swarms of agents.
He also describes the indie-researcher incentive problem: the odds of being heard are so low that the time is better spent elsewhere — though he offers to do one more well-scoped round offline. A candid look at how big labs fail to engage outside researchers.
More from coding & agent
- Master LLM evals step by step: read 100 traces by hand, then build a versioned golden dataset — datawithsuman · 2026-10-30
- Devs miss flow state with AI agents — faster loops from Cerebras may bring it back — vivekhaldar · 2026-10-30
- PixelRAG: pixel-native RAG with web screenshots hits 10.8k GitHub stars — adnan_hashmi · 2026-10-30
- Cognition benchmark: Gemini 4 Carbon scores 40% near-SOTA at $4.04 per task — scaling01 · 2026-10-30
- 1200 renders into a MiniMax H3 short film, dev open-sources ComfyUI take manager Picky — friedlc · 2026-10-30
- Team moved 60 agents off one shared API key: 4 lessons from the migration — No_Reindeer3079 · 2026-10-30