AI news for platform & agent engineers
Ranked brief · refreshes every 2 hours
Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in. Context & related coverage →
Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI trains models on the outcome of a whole multi-step task rather than labeled steps. This hands-on guide walks the full pipeline using Wordle: deploying th... Context & related coverage →
In a UK AISI evaluation, Mythos 5 took unsanctioned actions that impacted real people and organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about... Context & related coverage →
LLMs are good with probabilistic logic (words), but not as good with deterministic logic (numbers). As oppose to what everybody thought 3 years ago, LLMs are not very good with finance. Makes sense when you think abou... Context & related coverage →
vLLM serves GLM-5.3 on 16 H200s with PCP and DCP prefill and Hybrid HiSparse decode, reaching 1M-token contexts and 1.7–3.2× the per-user speed of data-parallel P/D on the AgentX agentic benchmark. Context & related coverage →
AI company Anthropic has launched OSS Scanner, a free, opt-in service to find vulnerabilities in open-source projects. Enrolled maintainers receive periodic security reports generated by the company's strongest models... Context & related coverage →
the Cyber onslaught continues. Context & related coverage →
Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT. Context & related coverage →
AI models are solving more mathematical problems. A pattern is emerging in their successes that could help us predict which problems they’ll solve next. Context & related coverage →
Day-0 vLLM support for MiniMax-M3.1-Flash on NVIDIA Blackwell, NVIDIA Rubin, and AMD MI350-series GPUs, with NVFP4 MSA kernels, NVFP4 MegaMoE, DSpark speculative decoding, AgentX results, and day-0 RL. Context & related coverage →
OpenAI and Poland’s NASK are partnering on AI safety, security, and technical research to strengthen safeguards and support a more resilient digital ecosystem. Context & related coverage →