A September 14, 2026 arXiv paper demonstrates "capability laundering," in which a weaker unaligned model splits a harmful task into benign subproblems, consults a stronger aligned model on each indepe…
Researchers introduced Declarative Attention (DA), a protocol that lets language models declare which parts of their context they need to attend to, reducing total attended tokens by 52.0% on Gemma-4-…
Ornith AI released Ornith-1.5-35B-A3B, a 35B-parameter mixture-of-experts model that activates about 3B parameters per token, trained via a self-improvement loop that jointly optimizes task generation…
The ARC Prize 2026 awarded its first $37,500 ARC-AGI-3 milestone prize on June 30th to Tufa Labs for 'The Duck,' a small open-source LLM that solves interactive reasoning tasks by writing and running …
Researchers at SPAR argue that language models can report on their own internal activations, a method called self-report, which is underexploited compared to external analysis tools. They test five op…