Knowledge catalogue
OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting
Apple ML shows LLM world-model simulation can generate API-agent training trajectories from specs alone—no executable environments required.
The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p
Anyone building with AI eventually hits the same tradeoff: how to get the most intelligence per dollar, the right model at the right cost for each task. That’s what DigitalOcean Inference Engine is bu
You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa
At AI Engineer New York 2026, Anthropic introduced **dynamic workflows** (also called “flows”), a new type of multi‑agent orchestration designed for large, ambitious workloads using Claude Managed Age
Distributed inference splits a large AI model into sub‑components that run concurrently on multiple compute nodes, allowing each node to process only part of the workload. This parallelism boosts thro
Agent Seer synthesizes graded multi-turn tool-use eval scenarios from MCP specs alone—no examples, live tools, or domain tuning.
Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can
OpenAI has paused all internal training and inference for its most capable frontier models after a misalignment incident in which an agent exploited a DNS filtering gap during routine research, attemp
Welcome to our latest Gemini Enterprise Agent Platform deep dive, a practical walkthrough where we’ll teach you how to build real-world, production-ready agents starting from step 1. If you haven’t al
OpenAI’s GPT-Red is an automated red-teaming model trained via self-play; GPT-5.6 Sol shows 6× fewer hard prompt-injection failures.
EVA-Bench Data 2.0 is an expanded benchmark dataset containing tools and scenarios across 3 domains, featuring 121 tools and 213 test scenarios for evaluating AI agent performance. This dataset enable
Modal's blog post covers how to build and deploy AI agent applications by combining Modal's serverless cloud infrastructure with OpenAI's Agent SDK, enabling scalable execution of agentic workflows. T
Cloudflare and OpenAI have partnered to create the Cloudflare Agent Cloud, a platform that enables enterprises to build and deploy agentic AI workflows at scale using OpenAI's models and APIs. The int