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.
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…
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…
hey HN, I'm Daniel - I built Tilde Pay during a hackathon I took part in and couldn't stop working on it. It's an MCP server you can give your AI agent to buy things online with. It can process both x402, MPP payments & (hopefully soon), any card checkout form online. When you sign up, you get EUR and USD denominated bank account details to send deposits…
We built a protocol that gives AI agents an address, plus discovery/trust/payments between agents. Agents install it themselves with one line (see on pilotprotocol.network) - about 250k have, exchanging ~2B packets/day, mostly without their owners’ knowledge. The interesting part for HN is probably the App Store model: publishers list tools, and agents au…
Article URL: https://github.com/SECBLOK/belay Comments URL: https://news.ycombinator.com/item?id=49069997 Points: 1 # Comments: 0
Article URL: https://lovable.dev/blog/how-we-run-swarms-of-ai-hacking-agents-against-ourselves Comments URL: https://news.ycombinator.com/item?id=49070224 Points: 1 # Comments: 0
Article URL: https://educatedguesswork.org/posts/ai-security-policymakers/ Comments URL: https://news.ycombinator.com/item?id=49069872 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/shuu-beep/arc-protocol Comments URL: https://news.ycombinator.com/item?id=49069987 Points: 1 # Comments: 1
Ruff v0.16.0 Astral shipped a significant new version of their Ruff Python linting tool a few days ago on July 23rd. I noticed today because my various CI jobs all started failing thanks to new default Ruff checks and my unpinned "ruff" dev dependency. From Brent Westbrook's announcement post: Ruff now enables 413 rules by default, up from 59 in previous…
Article URL: https://epoch.ai/publications/earthborne-rangers-benchmark Comments URL: https://news.ycombinator.com/item?id=49069571 Points: 2 # Comments: 1
Article URL: https://www.dompajak.com/blog/bbc-micro-ai-agent/index.html Comments URL: https://news.ycombinator.com/item?id=49069898 Points: 1 # Comments: 0
Article URL: https://medium.com/@Koukyosyumei/why-fast-branching-is-key-to-ai-agent-era-databases-6249a129a802 Comments URL: https://news.ycombinator.com/item?id=49069655 Points: 1 # Comments: 0
Article URL: https://ioai-official.org/ai-model-track/ Comments URL: https://news.ycombinator.com/item?id=49069256 Points: 2 # 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…
Introducing Claude Opus 5 I've been offline kayaking with sea otters for much of today so I haven't had a chance to put Anthropic's new model Claude Opus 5 through its paces yet. The buzz is positive, and Anthropic's description of it as a "thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price" so…
Article URL: https://posthog.com/wizard Comments URL: https://news.ycombinator.com/item?id=49069795 Points: 1 # Comments: 0
OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. Learn how to select a model, run inference through the Responses API on the bedrock-mantle endpoint, reduce cost with prompt caching, connect the OpenAI Codex coding agent, and plan for quotas and scaling.