Madison Lee retweeted
Web search is now part of how open-weight models get trained.
We teamed up with @nvidia and @CoreWeave to put @youdotcom search inside the RL loop for Nemotron 3.5 Lightning.
BrowseComp 36.97% → 45.45%. 30% fewer tool calls.
Smarter model, less searching. More to come with this crew!
In reinforcement learning, inference is part of the training loop. Every checkpoint used to mean a redeploy, and the trainer waited.
CoreWeave RL Rollouts load the new weights into a live deployment without touching in flight requests, about 15x faster than a redeploy cycle.
@nvidia and @youdotcom used it to post train Nemotron 3.5 Lightning for web search and lifted BrowseComp accuracy from 36.97% to 45.45% while cutting tool calls by 30.24%.
Full breakdown here: crwv.co/utdYc
Madison Lee retweeted
Web search is now part of how open-weight models get trained.
Partnering with with @NVIDIAAI and @CoreWeave, we've built a training stack that brings live web search into reinforcement learning, starting with @nvidia Nemotron 3.5 Lightning.
More to come as we open this up.
Madison Lee retweeted
Great work, @edwardirby!
Excited to see what people build with Jev + @youdotcom
How to build a reliable risk agent without a frontier model ($0.02/sweep):
• @youdotcom search
• @typesafeai Jev for typed judgments
• @QwenDevs for proposals & synthesis
• MCP for integration
Full architecture & cost breakdown below 👇
Madison Lee retweeted
Almost every prompt requires web search. We are happy to announce our partnership with @youdotcom for AnythingLLM.
Every user now will get accurate, fresh, and rich web-search with ZDR right out of the box. Server, Desktop, & Mobile.
Read more: anythingllm.com/blog/you-com…