StateM: harness scaling on Terminal-Bench 2.1
A runtime harness lifts GPT-5.6 Sol to 95.3 percent on Terminal-Bench 2.1 for about 15 dollars, without touching model weights.
Landmark Papers
What the papers actually said - linked to the originals.
676 entries, all primary-sourced
FreeToken: edge-native mixture-of-experts serving
A Berkeley-led system serves mixture-of-experts models up to 753B parameters on a single personal machine with an 8GB GPU.
Claude designs protein binders against 14 of 15 targets
Anthropic reports Claude autonomously designed 354 confirmed protein binders from 1,320 designs, succeeding on 14 of 15 targets.
Microsoft broadens access to Skala 1.1, a machine-learned density functional
Microsoft Research shipped Skala 1.1, trained on 2.5 times more data, reporting 2.8 kcal/mol weighted average error on GMTKN55.