430 stories
Lately I’ve been writing a lot about the sociopolitical considerations that economic-style reasoning misses. I view this work as continuous with my agent foundations research; in this post, I lay out some of the connections I see between sociology and agent foundations.
TL;DR: A safety case for scheming must be able to substantiate these four key claims: scheming was not incentivized during training, strong evaluations and red teaming suggest that the model does not have a propensity to scheme, scheming was never attempted during internal deployment, and scheming…
TL;DR: AI agent orchestration is the coordination of multiple agents, tools, models, and shared state, and in production it only works when operational controls run inside every agent, tool call, and handoff. Each orchestration pattern fails in its own way, so each needs its own controls.
Agents don't build trust for another reason, structurally worse than the first. It isn't only that the tool keeps changing shape. It's that the feedback loop you would need in order to learn the tool is broken at the point of measurement.
AI agents can now write CUDA kernels that outperform PyTorch—but proving those speedups are real is the harder problem. I put them to the test on an NVIDIA DGX Spark and found that benchmark design matters just as much as the code.
Docker Agent is an open-source, Apache 2.0-licensed CLI plugin built by Docker Engineering, installed and run as docker agent. Its own tagline states the goal plainly: run AI agents like containers.
Pratik Rasam discusses how Spotify Ads Manager runs production-grade multi-agent systems at scale using Google ADK Java. He shares key architectural patterns, domain ownership models, deterministic guardrails, and tracing-based evaluation strategies, detailing hard-learned lessons on drawing agent…
Have an idea for a lesson illustration, a project chart, or a comic for your next presentation? Nano Banana 2.1 lets you explore these formats with text prompts, making it easier to try different visual styles without switching between tools.
An agentic system issues several structurally different kinds of LLM calls. It routes intent, classifies actions, grounds language in a device registry, plans multi-agent pipelines and writes the Python code those pipelines run.
When agents share a reward for completed tasks, reporting unsafe work can reduce the reporter's reward by stopping a task. Audits can make reporting optimal without ensuring that further training teaches a silent team to report.
Agentic coding makes code generation cheap, but reliable completion remains difficult: the agent that writes the code is a weak judge of whether it is done.
The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier…
LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel multi-agent reasoning systems, where several agents solve the same problem over multiple rounds and aggregate their outputs into…
Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as lattice grids or standard sampling-based approaches, frequently face a trade-off between graph density and the…
Article URL: https://github.com/docker/docker-agent Comments URL: https://news.ycombinator.com/item?id=49996259 Points: 275 # Comments: 126
Qlik built Qlik Answers on Amazon Bedrock to give its 40,000+ customers grounded, sourced answers across structured and unstructured enterprise data. Learn how a layered, multi-agent architecture with cross-Region inference and Amazon Bedrock Guardrails delivers trusted AI at global scale.
The biggest barrier to AI adoption isn't awareness. It's the gap between talking about AI and building with it. Here's the playbook we used to turn non-technical, customer-facing professionals into confident AI builders in six weeks, and how your organization can replicate it.
Cornerstone OnDemand built Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, to turn database operations from reactive firefighting into proactive automation. A three-person team cut database diagnosis from 45 minutes to 10, a 78% reduction, in six months.
Showing 72 of 430 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
