Direct Preference Optimization Beyond Chatbots
Direct Preference Optimization Beyond Chatbots Using Rejection Pairs From Your Model's Own Failures In April, we released DharmaOCR, our specialized structured OCR model ( available on Hugging Face )
AI News
Adding MCP Tools to Reachy Mini
Reachy Mini no longer has to look out the window to tell you the weather Below, we look at what a tool is, how profiles control what the robot can use, and the current limits of the remote path. When
A blueprint for democratic governance of frontier AI
OpenAI outlines a blueprint for U.S. governance of frontier AI, proposing a federal framework for safety, resilience, and national security.
Holo3.1: Fast & Local Computer Use Agents
Holo3.1: Fast & Local Computer Use Agents Users want to run the same computer-use capabilities across desktop and mobile environments, with seamless integration with different agent frameworks. They w
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic Guides have aided humanity throughout history. Prehistoric civilizations understood that the sun and the moon could be used to n
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code. The model activates only 2.5B pa
Strengthening societal resilience with Rosalind Biodefense
OpenAI launches Rosalind Biodefense, expanding trusted access to GPT-Rosalind for vetted developers and U.S. government partners advancing biodefense, public health, and pandemic preparedness through
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler What you cannot profile, you cannot optimize. Whether you are trying to squeeze more tokens per second out of a Large Language Model
How Braintrust turns customer requests into code with Codex
How Braintrust engineers use Codex with GPT-5.5 to run experiments and code faster.
A shared playbook for trustworthy third party evaluations
OpenAI shares guidance on third-party AI evaluations, covering how to assess model capabilities, safeguards, and validity for frontier systems.
Boston Children’s uses AI to unlock new diagnoses
Boston Children’s Hospital uses OpenAI technology to improve patient care, reduce operational burden, and help diagnose more than 40 rare disease cases.
How Endava builds an agentic organization with Codex
Learn how Endava uses Codex to build an agentic organization, accelerating software delivery and reducing requirements analysis from weeks to hours.
OpenAI’s Frontier Governance Framework
Explore OpenAI’s Frontier Governance Framework and how our AI safety, security, and risk practices align with emerging EU and California regulations.
Cisco and OpenAI redefine enterprise engineering with Codex
Cisco and OpenAI are redefining enterprise engineering with Codex, helping Cisco scale AI-native development, accelerate AI Defense work, and automate defect remediation.
Election information and safeguards in 2026
Learn how OpenAI is supporting elections in 2026 through reliable information, cyber defense, AI transparency, misuse safeguards, and bias monitoring.
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL Async RL has a dirty secret: every step, the trainer has to ship the whole model to the inference engine. For a 7B in bf16 th
Reachy Mini goes fully local
This stack is powered by speech-to-speech , our cascaded VAD → STT → LLM → TTS pipeline that exposes a Realtime API-compatible /v1/realtime WebSocket. Once you launch the backend, point the robot at i
Building self-improving tax agents with Codex
See how OpenAI, Thrive, and Crete built a self-improving tax agent with Codex, automating filings, improving accuracy, and accelerating workflows.
Warp’s big bet on building open source with GPT-5.5
Warp uses GPT-5.5 and OpenAI models to coordinate coding agents across local, cloud, and open-source development workflows.
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
Harness, Scaffold, and the AI Agent Terms Worth Getting Right This can be overwhelming for newcomers, and even for practitioners trying to keep up with the latest developments. After ICLR 2026, one of
Follow & Subscribe
Get the latest updates on Facebook and Telegram
Follow on Facebook
Scan with your phone
Scan with your phone Join on Telegram
Scan with your phone
Scan with your phone