Cognition's SWE-2 coding model scored 83.75% on the eight-task KingBench 3 benchmark, beating DeepSeek V4.1 Flash at 81.25% and its own base model Kimi K3 at 77.5%, according to independent testing. S…
An engineer optimized an 8GB NVIDIA Jetson Orin Nano for headless ROS 2 and edge-AI, reducing idle RAM usage from 913 MiB to 699 MiB by disabling the graphical desktop and unnecessary services. The gu…
ModelBest and Tsinghua University released MiniCPM-5, a 1-billion-parameter on-device AI model with a 128K context window and native tool-use capabilities, designed for agentic workflows on phones and…
A researcher trained a cheap Gemma 2B judge to detect misalignment in AI agents, but testing against Anthropic's AuditBench showed the judge failed to reduce audit costs or reliably distinguish misali…