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.
Hi HN! I've been working on Bor, an open-source system for centralized Linux desktop management. Bor consists of a lightweight Go agent and a central server. Policies are streamed to clients over mTLS/gRPC in real time—no polling—and currently support Firefox, Chrome, KDE, dconf, polkit and package management, with more coming. Version 0.8 introduces seve…
Article URL: https://www.wafer.ai/blog/kimi-k3-mi355x Comments URL: https://news.ycombinator.com/item?id=49141073 Points: 169 # Comments: 85
Tuesday was Stateless MCP day - the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant change to the MCP spec since it first launched, and has also served to reignite my personal interest in the protocol. For background: MCP is the Model Context Protocol,…
Rails Agent - The Fullstack Agentic Development Platform For Ruby on Rails. Build, Test, Deploy & Monitor in one single dashboard. Advanced alternative for RubyLLM and Active Agent Comments URL: https://news.ycombinator.com/item?id=49145011 Points: 1 # Comments: 0
Article URL: https://github.com/pochenai/nano-llm-posttraining Comments URL: https://news.ycombinator.com/item?id=49133851 Points: 21 # Comments: 0
Advancing the price-performance frontier with GPT‑5.6 Huge price drop from OpenAI today: GPT-5.6 Terra got a 20% reduction, and GPT-5.6 Luna got a massive 80% drop. OpenAI credit 5.6 Sol with enabling this: in How GPT‑5.6 fuses frontier intelligence with frontier efficiency they describe using 5.6 Sol to optimize load balancing, and more impressively to o…
Investigating three real-world incidents in our cybersecurity evaluations It happened again! This is turning into something of a pattern. Last week OpenAI accidentally exploited Hugging Face when one of their frontier models broke out of a sandboxed container and hacked into Hugging Face to try and get the solutions to the cyber benchmark it was executing…
Article URL: https://github.com/xcreener/xcreener-mcp Comments URL: https://news.ycombinator.com/item?id=49145092 Points: 1 # Comments: 0
Article URL: https://github.com/lace-ai/gai Comments URL: https://news.ycombinator.com/item?id=49129430 Points: 3 # Comments: 0
Article URL: https://jwlabs.vercel.app/post/speculative-decoding-first-principles Comments URL: https://news.ycombinator.com/item?id=49130093 Points: 2 # Comments: 0
Article URL: https://github.com/OmegaAgent/handoff Comments URL: https://news.ycombinator.com/item?id=49143842 Points: 1 # Comments: 1
Article URL: https://runtimewire.com/article/arrakis-security-raises-8-million-ai-agent-runtime-controls Comments URL: https://news.ycombinator.com/item?id=49144865 Points: 2 # Comments: 0
Article URL: https://github.com/ANIRudH-lab-life/job-radar Comments URL: https://news.ycombinator.com/item?id=49141408 Points: 4 # Comments: 0
Article URL: https://zenodo.org/records/21753002 Comments URL: https://news.ycombinator.com/item?id=49140080 Points: 10 # Comments: 4
I use the terminal a lot, but I don't remember every command, flag, and syntax available. ffmpeg, piping to awk, find, etc... I know I'm not cool enough, but it's crazy-making. I get into a regular pattern of asking Claude, ChatGPT, or a local model how I'd write a command or do something with some files or a prompt, then going back to the terminal with a…
Article URL: https://nochan.net/b/Internet-Crap/20260714-Do-Not-Trust--Continuously-Verify/ Comments URL: https://news.ycombinator.com/item?id=49144956 Points: 2 # Comments: 0
https://github.com/jwlaboratory/bite-the-bullet Comments URL: https://news.ycombinator.com/item?id=49127874 Points: 41 # Comments: 4
deepseek-ai/DeepSeek-V4-Flash-0731 The latest release in DeepSeek's V4 family, "with substantially enhanced agentic capabilities". It's 304 billion parameters - 167GB on Hugging Face - but it appears to punch well above its weight. Artificial Analysis rank it ahead of MiniMax M3 - a 428B model. It's $0.14/million input and $0.27/million output pricing mea…