Does a context gate for search agents actually work?
Testing context gating on BrowseComp-Plus. A cheap label-free gate cuts a search agent's input tokens 1.4x, gate costs included, no detectable accuracy change.
Blog
Latest thoughts on LLMs, engineering, and data science
Which H100 instance to train Nanochat
Benchmarking H100 PCIe vs SXM vs NVL on training cost, step times, and NCCL profiling to find the cheapest GPU configuration for Nanochat
Why Model Context Protocol (MCP)?
Enabling endless capabilities for LLMs
Making LLM workflows human friendly
Validate the data as it streams, don't make your users wait.