AI news for platform & agent engineers
Ranked brief · refreshes every 2 hours
Decision models have exploded onto the scene recently, starting with TypeSafe’s Jev, followed by Perplexity’s Decider, Liquid’s d1, Cloudflare’s Clef, and OpenAI’s Decisions API 1 . These models promise fast, inexpens... Context & related coverage →
Participating in a data space still requires the Dataspace Protocol (DSP) negotiation flow to be hand-coded against each provider's access policy. We present a multi-agent architecture that automates this process usin... Context & related coverage →
The speakers discuss transitioning AI agents from local FastAPI prototypes to resilient production systems on Kubernetes using Ray. They share operational insights on RayCluster topology, stateful memory handling, aut... Context & related coverage →
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of... Context & related coverage →
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmark... Context & related coverage →
My obituary for programming Jeremy Scheff poignantly captures the key loss caused by coding agents for career programmers who enjoyed the puzzle of developing code: Programming turned into one of the greatest jobs you... Context & related coverage →
We benchmarked NVIDIA's new Arm-based Vera CPU on agentic Sandbox workloads. Under heavy load, it completes far more tasks than the x86 and Graviton alternatives, without sacrificing latency. Context & related coverage →
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce subs... Context & related coverage →
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be rel... Context & related coverage →
Earlier this month at Gemini at Work, we introduced the Gemini agent: a single, universal agent for work. It answers your questions, handles your knowledge work, creates your images and media, and writes and runs code... Context & related coverage →