A compact digest of model releases, papers, agentic systems, coding automation, infra, security, and high-signal developer discourse. Feed candidates are ranked locally; the scheduled Hermes worker can add qualitative synthesis.
awsmux fans one AWS CLI command out across hundreds of accounts and regions in parallel and merges the results into a single stream. There's an MCP server built in for agents. In a 150-session benchmark, agents using awsmux beat agents using the raw AWS CLI in every test: up to 5.4x faster, up to 2.9x cheaper, up to 7.4x fewer tokens. Single Go binary, st…
Earlier this month I hosted a fireside chat session at the AI Engineer World's Fair with Cat Wu and Thariq Shihipar from Anthropic's Claude Code team. We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves. The full video of the session is now available on YouTube . Below is…
Article URL: https://tobi.knaup.me/2026-07-25-open-weight-ai-is-having-its-kubernetes-moment/ Comments URL: https://news.ycombinator.com/item?id=49048034 Points: 277 # Comments: 222
Article URL: https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models Comments URL: https://news.ycombinator.com/item?id=49051361 Points: 82 # Comments: 41
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke its way out of OpenAI's sandbox, then found exploits to break in to Hugging Face, all so it could cheat on the test by stealing the answers. Along the way i…
Article URL: https://pytorch.org/blog/bringing-pytorch-monarch-to-amd-gpus-single-controller-distributed-training-on-rocm/ Comments URL: https://news.ycombinator.com/item?id=49048689 Points: 56 # Comments: 6
The UK MET office recently redesigned their site, adding a lot of additional whitespace, scrolling, and animations. This significantly reduced its usability for me, and left me wanting an ‘at a glance’ weather site. I made https://brolly.sh , a minimalist, plain text weather forecasting site. You can use it to view weather from around the world, with: 7 d…
I like writing Markdown, but do not like writing it inside a plain textarea. I wanted something I could use anywhere by dropping in a single web component: ``` ``` That became Writemark. It renders Markdown while you write, but Markdown remains the value you read, store, and submit. It also has source, split, and preview modes, along with slash commands,…
Article URL: https://www.debian.org/vote/2026/vote_002 Comments URL: https://news.ycombinator.com/item?id=49050859 Points: 17 # Comments: 6
Article URL: https://claude.ai/public/artifacts/725f961b-09dc-4a66-8dac-8fefeeb69a1f Comments URL: https://news.ycombinator.com/item?id=49050803 Points: 10 # Comments: 5
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-sour…
The first known runaway AI agent - or a very bad marketing stunt? Martin Alderson's commentary on the OpenAI accidental cyberattack against Hugging Face includes a couple of details I hadn't considered. First, Hugging Face offers a truly rich target if you're trying to find potential vulnerabilities that require executing arbitrary code: Hugging Face has…
Article URL: https://vettedconsumer.com/speculative-decoding-explained-the-free-speed-toggle-your-local-llm-is-probably-not-using/ Comments URL: https://news.ycombinator.com/item?id=49044237 Points: 4 # Comments: 0
Article URL: https://zenodo.org/records/21566453 Comments URL: https://news.ycombinator.com/item?id=49049884 Points: 2 # Comments: 0
Inspired by Crypto Pool Mining: would it be possible to train LLMs as a pool of volunteers? I feel like that would be a good way to have frontier models that are open and don’t rely on big corporations with data centers to train and release them… Comments URL: https://news.ycombinator.com/item?id=49048332 Points: 2 # Comments: 2
Article URL: https://github.com/ghdtjrtka/ghost-vessel Comments URL: https://news.ycombinator.com/item?id=49036748 Points: 1 # Comments: 0
In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can reason, plan, and act by orchestrating calls to foundation models (FMs) and external tools. The solution uses large language models (LLMs), Amazon Bedrock, and Amazon Bedrock Knowledge Bases. It als…
Article URL: https://instavm.io/blog/how-code-mode-can-help-smaller-llm-models Comments URL: https://news.ycombinator.com/item?id=49045767 Points: 2 # Comments: 0