@mayhewsw: New paper: I know the hotness is all in 10xing compute scale, and telling things to think step by step with tool use, b…

X AI KOLs Following Papers

Summary

Authors release Universal NER v2, a named-entity recognition paper presented at LREC 2026 that deliberately eschews modern scaling and tool-use trends.

New paper: I know the hotness is all in 10xing compute scale, and telling things to think step by step with tool use, but me and my crew are still publishing papers that could have been written in 2003. Introducing: Universal NER v2, at LREC 2026
Original Article

Similar Articles

@dair_ai: https://x.com/dair_ai/status/2056018543850754283

X AI KOLs Following

A roundup of the top AI papers from May 11-17, covering Lighthouse Attention for long-context pretraining, a comparison of grep vs embedding retrieval for coding agents, and mechanistic interpretability work revealing a geometric calculator in LLMs.

@dair_ai: NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, mat…

X AI KOLs Following

A new paper shows that using a weak model with k=8 proposals and a critic-comparator selection loop can match frontier model performance on SWE-bench Verified, reaching 76.4% accuracy. The key insight is that correct patches are often already present in a weak model's top-k candidates, and the challenge is effective selection using execution verification.