what are the best evals for deep-research-esque llm search agents apart from simpleQA and HLE?

Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models. (Joint work with Ayush Chakravarthy, Ryan Ehrlich, Sabri Eyuboglu, Bradley Brown, Joseph Shetaye,

why can't LLMs do this?

How can we close the generation-verification gap when LLMs produce correct answers but fail to select them? 🧵 Introducing Weaver: a framework that combines multiple weak verifiers (reward models + LM judges) to achieve o3-mini-level accuracy with much cheaper non-reasoning

ask (very!) complex questions about open source repos using Dosu Public Spaces dosu.dev/blog/july-dosu…

PSA: You can now explore available free Public Spaces for popular Open Source projects using our new Explore page! Link in reply 👇