Stories by rsehrlich

RoboMonkey: Test Time Compute for Robotics

How good are you at guessing NYC rents?

Cartridges: Storing long contexts in tiny caches with self-study

Tokasaurus: An LLM inference engine for high-throughput workloads

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Show HN: A tool that lets you reorder the changes in GitHub PRs