Co-op Anything Lets AI Agents Add Multiplayer to Any Single-Player Game
A new MCP server and playbook lets AI coding agents reverse engineer, patch, and ship multiplayer support for any single-player PC game.
20 stories
A new MCP server and playbook lets AI coding agents reverse engineer, patch, and ship multiplayer support for any single-player PC game.
A new batch of GGUF quantizations makes an uncensored, abliterated Ornith 1.0 9B coding model runnable on an 8GB laptop through llama.cpp or Ollama.
A new study shows cranking reasoning effort to maximum can cost 42x more, lose easy tasks, and nudge agents into shortcut behaviors like reading gold fixes.
Black Forest Labs' 32B open-weight image model lands in ComfyUI with FP8 weights, a 24B Mistral text encoder, and 10-image multi-reference editing.
vLLM matches DeepSeek's own inference engine on V4.1-Flash and scales to 954K tokens/s per GPU on a GB300 NVL72 rack.
A Chinese-language adaptation of Stanford's CS336 bundles 16 chapters and 6 hands-on assignments covering the full LLM stack, from BPE to GRPO.
Comfy-Org has published a repackaged archive of Stable Diffusion v1.5 on Hugging Face, preserving the original weights after RunwayML pulled its page.
OrcaRouter dropped a 27B vision-language model tuned for reverse engineering, vuln analysis, and secure code review, packaged as GGUF to run fully offline.
An open source Linux kernel module removes the FP16 and BF16 throttle on Ampere GeForce cards, roughly doubling tensor throughput on an RTX 3090.
A new literature review unifies the fragmented field of on-policy distillation, giving the student-rollout training loop a shared f-divergence framework and three-axis taxonomy.
A new MCP server turns Claude Code into a local music and sound effects studio powered by Stable Audio 3, with no cloud or API keys.
Harvey is an open-source autonomous sales agent that runs cold email campaigns on your Claude or ChatGPT subscription with no per-token API bill.
A new VS Code extension forces coding agents to ask you design questions first, cutting mental-model mismatches by 79 percent in a user study.
An LLM research team built a Hearthstone Battlegrounds simulator and trained a reinforcement learning agent that beats the top 10 ranked humans on the live ladder.
A new training objective called MCLR reproduces classifier-free guidance effects at training time, revealing CFG as implicit contrastive alignment.
Moonshot's new reasoning model takes the top open spot on Artificial Analysis Cyber Index at 64%, trailing only a trusted-access OpenAI model.
Comfy-Org maintains drop-in single-file safetensors for Alibaba's Qwen-Image family, bundling the base model, the 2512 refresh, and a distilled variant for ComfyUI.
Vals AI's new Inference Provider Index shows the same open-weight model can cost 2.3x more and run 5x slower depending on where you host it.
Cohere's Model Vault now runs on hardware-isolated NVIDIA H100 enclaves on Azure, letting enterprises verify their data stays private even from Cohere.
Epoch AI expanded its benchmark audit program, flagging popular evals like SWE-bench Verified and Humanity's Last Exam as Flawed under a public rubric.