Automated research agent finds silent numerical bug in FlashInfer kernels; fix PR accepted
timshi_ai · x · 2026-08-28
An automated research system scored a real win: Josh Tobin's team had previously built a reward-hacking judge for performance optimization tasks. While applying it to new autoresearch work, the system discovered that some FlashInfer kernels (the library underpinning vLLM and SGLang) used a hardcoded value of -50,000 as a masked-attention sentinel — even though valid QK values can be smaller.
Such silently-wrong corner cases are notoriously painful to find (recall the historical flash-attention debate). The system not only located the issue but submitted a fix PR, which human experts accepted.
Related event: Automated AI Research Agent Finds Numerical Bug in FlashInfer Kernels(3 posts)→
More from coding & agent
- AI eliminates the cognitive strain and mental fatigue of programming — signulll · 2026-08-28
- Antirez Open Sources Code, Invites Agents to Use It — antirez · 2026-08-28
- DeepSeek Open Source Project Hits 200k Stars with Plugin-Based Design — omarsar0 · 2026-08-28
- Context Engineering Guide: Structuring Info for Reliable Agents — Pavan_Belagatti · 2026-08-28
- AI agents might expose sensitive data buried in Git history — doodlestein · 2026-08-28
- Using Agents and Small Models to Bootstrap Object Detection Data — vanstriendaniel · 2026-08-28