Terminal-Bench 4
PulseAugur coverage of Terminal-Bench 4 — every cluster mentioning Terminal-Bench 4 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Factory releases Droid 1.0 coding agent with programmatic tool calling
Factory has released Droid 1.0, an updated model-independent coding agent harness that defaults to programmatic tool calling. This new feature allows the model to write JavaScript programs that execute tools within a sa…
-
Recursive Self-Rewrite framework boosts AI model performance on complex tasks
Researchers have introduced Recursive Self-Rewrite (RSR), a novel framework designed to enhance AI model performance on complex tasks. RSR utilizes a base model, Qwen-3.8-27B, to discover and reconstruct successful solu…
-
New research explores optimizing agent harnesses for improved AI performance · 9 sources tracked
Multiple research papers explore the optimization and evolution of agent harnesses, which are crucial components that dictate how language models interact with their environments. Studies introduce novel frameworks like…
-
Cognition's SWE-2 coding model matches Fable 5.1 at lower cost
Cognition has released SWE-2, a new coding model post-trained using reinforcement learning from Moonshot AI's Kimi K3 model. This new model reportedly matches Fable 5.1's performance on the FrontierCode benchmark but at…