01
OpenAI just open-sourced Codex Security
Article URL: https://github.com/openai/codex-security Comments URL: https://news.ycombinator.com/item?id=49089755 Points: 216 # Comments: 44
Daily AI development intelligence, filtered for builders.
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.
Showing top signal · 18 items
No items in this section yet. The next refresh may surface relevant links here.
02
Show HN: XY – A Fast, composable, GPU-accelerated interactive plotting library
Article URL: https://github.com/reflex-dev/xy Comments URL: https://news.ycombinator.com/item?id=49085798 Points: 100 # Comments: 40
03
Discovering Cryptographic Weaknesses with Claude
Article URL: https://www.anthropic.com/research/discovering-cryptographic-weaknesses Comments URL: https://news.ycombinator.com/item?id=49087091 Points: 149 # Comments: 77
04
A Fireside Chat with Cat and Thariq from the Claude Code team
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…
05
Anthropic publishes a practical key-recovery attack on HAWK-256
Article URL: https://github.com/anthropics/cryptography-research-demo Comments URL: https://news.ycombinator.com/item?id=49090083 Points: 31 # Comments: 2
06
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
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…
07
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure . This attack was very sophisticated, and the resulting document doubles as a crash-course in modern adversarial security a…
08
Kimi K3: Open Frontier Intelligence
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined tra…
09
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Article URL: https://arxiv.org/abs/2607.24625 Comments URL: https://news.ycombinator.com/item?id=49085888 Points: 2 # Comments: 0
10
Show HN: Fast, local, lossless JSON formatting checks for coding agents.
Article URL: https://github.com/skrcode/bestjsonformatter-cli Comments URL: https://news.ycombinator.com/item?id=49087894 Points: 2 # Comments: 0
11
Show HN: Opensource resume evaluation LLM agents
Hyre turns a resume PDF into markdown, runs it through an LLM pipeline for layout analysis, data extraction, and scoring. It then evaluates a score for the resume. Comments URL: https://news.ycombinator.com/item?id=49072939 Points: 1 # Comments: 0
12
Distilling proprietary model reasoning into open-source search agents
Article URL: https://arxiv.org/abs/2607.24280 Comments URL: https://news.ycombinator.com/item?id=49087304 Points: 4 # Comments: 0
13
Why Hardware Engineering is the next target for Agents
Article URL: https://assistedeverything.substack.com/p/the-age-of-agentic-engineering-for-hardware Comments URL: https://news.ycombinator.com/item?id=49085109 Points: 2 # Comments: 0
14
Show HN: Mustuse.ai – Open-source automated ranking system run by agents
Hi HN, MustUse.ai is an open-source framework for building ranking sites that Codex agents can fully research and maintain automatically. Friends often ask me which AI tools they should use for different tasks. I wanted a ranking I could trust and point them to, but many of the lists I found were full of ads, affiliate incentives, or sponsored placements.…
15
AI-coding agents kill team collaboration
Article URL: https://leaddev.com/ai/ai-coding-agents-kill-team-collaboration Comments URL: https://news.ycombinator.com/item?id=49086140 Points: 3 # Comments: 0
16
Vectorise.me – image-to-SVG API with an MCP server for AI agents
Article URL: https://vectorise.me/developers Comments URL: https://news.ycombinator.com/item?id=49085515 Points: 2 # Comments: 0
17
Hugging Face rebuilt a third of its infrastructure after OpenAI agents ran amok
Article URL: https://www.theregister.com/ai-and-ml/2026/07/28/openais-agent-siege-forced-significant-rebuild-at-hugging-face/5279577 Comments URL: https://news.ycombinator.com/item?id=49084497 Points: 8 # Comments: 0
18
Scientific computing in the age of agentic AI
A new field report shows how scientists use AI coding agents to modernize scientific computing, accelerating software development and discovery in genomics and beyond.