You.com: agentic search failures are behavior problems, fixed in Nemotron 3.5 Lightning
RichardSocher · x · 2026-10-29
You.com (RT'd by Richard Socher) argues most agentic search failures are behavior problems, not knowledge problems: death loops, weak tool use, and doubting the answer after finding it.
You.com, NVIDIA and CoreWeave fixed these via post-training in 3 weeks, producing Nemotron 3.5 Lightning. The attached slide shows 36.97% on BrowseComp with the base model plus search tool, using 68+ tool calls per task.
More from Models
- Ex-Google Researcher's Elorian Launches Glimpse: Frontier Models Fail 50% on Visual Counting Benchmark — Latent Space · 2026-10-29
- Developer replaces Siri with local LFM3-Audio-2B, cutting home control latency from 3s to 0.54s — gregbarbosa · 2026-10-29
- 48h of AI chaos: Anthropic IPO, GPT-6.1 Terra, Genie 4, and a Gamma 5 agent demo — dr_cintas · 2026-10-29
- FrontierSWE leaderboard: GPT-6 Astra tops at 65.5%, Gemini 4 Carbon scores 61.2% at 1/16th the cost — scaling01 · 2026-10-29
- DeepSeek Flash fingerprint change hints at migration to a new GPU cluster — teortaxesTex · 2026-10-29
- Google admits human review error in Gemini policy flags, reverses account strikes — RexDouglass · 2026-10-29