Beat
Research
7 stories.
·Hugging Face
Ai2 updates climate emulator to cut extreme-weather simulation cost 300x
HiRO-ACEv2 matches a storm-resolving model's extremes but can't yet handle a warmer world
·arXiv cs.AI
Study: API benchmarks don't match chatbot app performance
Researchers say the gap can equal a full model version downgrade
·OpenAI
OpenAI publishes new math results from an internal frontier model
Lean proofs and ChatGPT Pro compute estimates follow advice from an outside math-AI group.
·arXiv cs.AI
Benchmark finds LLM-generated GPU kernels fail in production
FastKernels shows kernel-level speedups mostly vanish once agents' code runs inside real models.
·arXiv cs.LG
Study: post-training expands, not just compresses, hard reasoning
A diagnostic probe finds post-training raises the solvable ceiling on hard math problems, not just the odds of sampling a known answer.
·arXiv cs.AI
Study: French costs up to 58% more tokens than English across 7 LLMs
A paper measures a persistent "language tax" in 2026 tokenizers, and tests a French-optimised alternative to Mistral's Tekken.
·arXiv cs.AI
Study: DeepSeek-R1-Distill benchmark gains hard to reproduce
A paper finds reasoning-model benchmark scores swing widely with small changes to evaluation setup, undercutting claimed gains.