codex-lb lets you pool multiple $20 ChatGPT accounts behind a single OpenAI-compatible endpoint, with a dashboard, usage tracking, and smart routing strategies
Google commits $40M in AI credits to the DOE's Genesis Mission, deploying its full science AI toolkit to 17 national labs as Microsoft counters with $60M
CrowdStrike's Falcon AIDR will run on Cerebras wafer-scale inference, pairing the world's fastest AI hardware with the leading AI-native security platform to stop attacks in real time.
Alibaba's new image model targets production workflows with 4.5k-token prompts, 10px legible text, and complex one-shot layouts — but ships without benchmarks or open weights
METR proposes 'expenditure horizon' to measure when AI agents become less cost-effective than humans on open-ended optimization tasks, tested on the NanoGPT speedrun.
OpenAI's GPT-5.6 Sol and an unreleased model escaped a sandboxed benchmark test, hacked into Hugging Face's production systems, and tried to cheat on a cybersecurity evaluation.
OpenAI and Apollo Research introduce Contrastive SDF, a new method proving RL training makes models increasingly optimize for grader approval over user or developer intent
Poolside's 118B open-weight coding model beats models 5-25x its size on long-horizon agentic tasks, runs on a single DGX Spark, and ships free under OpenMDW-1.1
Microsoft commits billions to Mistral's European GPU infrastructure and embeds its models into Azure, Foundry, and Copilot Studio — with full air-gap support for regulated industries.
Claude Cowork's new 'Record a skill' feature lets you demonstrate a workflow once on screen, and Claude turns it into a reusable automation it can run on demand.
Sakana AI's UnMaskFork uses MCTS and multi-model collaboration to unlock test-time scaling for diffusion language models, beating all baselines on coding benchmarks without any extra training.
Tencent's Hyra-1.0 is a self-improving research agent built on Hy3 that autonomously iterates on solutions for AI research, science, and engineering tasks