Deep Principle’s open-weight Hydrogen-1.0 learned from lab notebooks and says it beats GPT-6-Astra at research science. The scores are its own.
Tag: research
SemiAnalysis’s new GDPx benchmark: 206 agent tasks in 11 domains. Claude Opus 5.5 leads at just 12%. How the models fail is the real story.
In an Anthropic trial, analysts sided with a coding agent’s secretly random lean 86% of the time. Few mentioned the agent at all.
OpenAI says an internal model disproved the Exponential Time Hypothesis, with a Lean proof. Two of the hypothesis’s authors will now check it.
Ai2’s open OlmoEarth v1.3 maps every 10m of land for 2023–2025 as searchable embeddings. It beats Google’s rival in most of its own tests.
Hugging Face’s open Carbon-X reads raw DNA in a chat and answers in English. Near-frontier on its own tests, at a fraction of the cost.
Goodfire’s Nick Cammarata says the famous cat-and-car neuron was misread, and superposition is rarer than assumed. Other researchers are unconvinced.
Ai2’s open FairStress benchmark tests whether AI models hold fair decisions under pressure. The ones tested bent more easily one way.
MemTensor’s open MemT models fold each chat into a fixed-size internal memory, then drop the transcript. 66x less storage, by their own numbers.
Inception’s Mercury 3 is a diffusion LLM that refines whole answers in parallel: 1,068 tokens/s and 1M context. The benchmarks are its own.