Lightweight AI Coding Agents Now Live Inside Your Terminal
Nanobot squeezes a full agent into ~4,000 lines of Python. That number. Not any launch deck. Tells you...
AI Accelerator Co-design: A3C3 Searches Both Sides at Once
A3C3 landed on arXiv June 24, 2026 carrying one argument: AI accelerator co-design should be a single automated...
Open-Sora 2.0 Trained a Commercial Video Model for $200k
Open-Sora 2.0 is an 11-billion-parameter, fully open-source video generation model released on March 12, 2025 by hpcaitech. The...
Programmable World Models: Where Agents Fail Cheap
A programmable world model is, at bottom, a rehearsal room. The agent acts, a learned simulation answers, nothing...
LLM Citations Are Guesses. Source Tracking Makes Them Receipts
C²-Cite raised citation quality by an average of 5.8% and response correctness by 17.4% on the ALCE benchmark....
Procedural Graph Architectures Are Rewiring Self-Evolving Agents
Graph-of-Agents landed at ICML 2025 with a blunt message for anyone shipping LLM agent pipelines: procedural graph architectures...
Open-Source LLM Toolchains Now Run Entirely Local
Somewhere past 130,000 GitHub stars, Ollama stopped being a curiosity and became the front door everyone walks through....
Open-Source Multimodal LLMs Now Take Audio and Video Natively
Open-source multimodal LLMs stopped pretending video is just a pile of images with a transcript stapled on. Qwen3-Omni...
Open Source Long Context LLMs Went 1M. Demand Proof.
Qwen 4 now ships a native 1M-token context window under an Apache 2.0 license. And the open source...
WearableQA Tested 14 Models. Most Fell Below 60%.
WearableQA put 14 big language models through 4,084 health questions built from real wearable data. And most of...