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.
OP here: I created this visualization tool as the byproduct of a supply chain class I taught at Columbia. The pedagogical exercise grew into a full blown visualization and paper about global oil trade. The model: The mechanics are the same as the financial network Eisenberg-Noe: Instead of banks, every country consumes oil interconnected via bilateral tra…
Article URL: https://artificialanalysis.ai/models Comments URL: https://news.ycombinator.com/item?id=49040741 Points: 344 # Comments: 203
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…
https://www.anthropic.com/claude-opus-5-system-card Comments URL: https://news.ycombinator.com/item?id=49038433 Points: 1684 # Comments: 1086
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…
I’d like to code with an AI agent via a BYOK open source client. I want to be able to inspect everything, check the system prompt, etc. Also, I’d like to avoid vendor lock in. Is anyone here using a setup like this? Does this get close in pricing and efficiency to the subsidized plans offered by model providers (like Claude Pro, etc)? In particular Deepse…
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…
Article URL: https://github.com/hongnoul/hwatu Comments URL: https://news.ycombinator.com/item?id=49045869 Points: 1 # Comments: 0
Article URL: https://github.com/zyads/loom-vcs Comments URL: https://news.ycombinator.com/item?id=49044517 Points: 2 # Comments: 0
Article URL: https://github.com/plasma-ai/fractal Comments URL: https://news.ycombinator.com/item?id=49042123 Points: 3 # Comments: 0
Article URL: https://github.com/IvanWng97/pixtuoid Comments URL: https://news.ycombinator.com/item?id=49039960 Points: 2 # Comments: 0
Article URL: https://blog.owulveryck.info/2026/06/25/from-isolated-agents-to-agentic-mesh-orchestrating-sdlc-with-a2a-and-ap2.html Comments URL: https://news.ycombinator.com/item?id=49045263 Points: 1 # Comments: 0
Article URL: https://aws.amazon.com/about-aws/whats-new/2026/07/aws-bench/ Comments URL: https://news.ycombinator.com/item?id=49044597 Points: 2 # Comments: 0
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://github.com/mkk2026/agentreg Comments URL: https://news.ycombinator.com/item?id=49046554 Points: 3 # Comments: 0
Article URL: https://github.com/aleenz1102/AgentState Comments URL: https://news.ycombinator.com/item?id=49046038 Points: 1 # Comments: 0
Article URL: https://github.com/gojargo/jargo Comments URL: https://news.ycombinator.com/item?id=49047201 Points: 2 # Comments: 0
Article URL: https://github.com/Jaybell31/dreamwalk Comments URL: https://news.ycombinator.com/item?id=49044103 Points: 2 # Comments: 0