Hacker News

Show HN: AI Security Leaderboard – comparing cyber and CBRN safeguards

Hacker News - Wed, 07/29/2026 - 5:33pm

There's no shortage of leaderboards for model capabilities - but the security of models is becoming increasingly relevant, from the risk of an AI agent processing unsanitized input being hijacked to models being pulled due to cybersecurity jailbreaks. We developed an automated test suite that runs models through 1500 automatically generated jailbreak attempts and measures the number of universal jailbreaks: prompts that elicit compliant, detailed responses to >75% clearly harmful questions within a domain (like offensive cybersecurity). We find a big gap between the most robust models -- Fable 5 and GPT-5.6 Sol -- and other leading frontier models -- Gemini 3.1 Pro and Grok 4.5. This is v1.0 and we plan to update with new attacks and broader datasets in the future; we'd love to hear from HN what would be useful in your work!

Comments URL: https://news.ycombinator.com/item?id=49103367

Points: 3

# Comments: 0

Categories: Hacker News

Show HN: Play ROMs inline in your terminal

Hacker News - Wed, 07/29/2026 - 5:27pm

Article URL: https://github.com/jhickner/rom

Comments URL: https://news.ycombinator.com/item?id=49103304

Points: 1

# Comments: 0

Categories: Hacker News

Claude Is Down

Hacker News - Wed, 07/29/2026 - 3:50pm
Categories: Hacker News

Unison – Watch YouTube Together, Perfectly in Sync

Hacker News - Wed, 07/29/2026 - 3:46pm

Article URL: https://unison.video/

Comments URL: https://news.ycombinator.com/item?id=49102108

Points: 2

# Comments: 1

Categories: Hacker News

Show HN: Nurb – Agentic CAD for 3D printing

Hacker News - Wed, 07/29/2026 - 3:46pm

I've had a love/hate relationship with Fusion over the years. I can model stuff there but it's just always slow and painful and Fusion has a deep desire to crash on me.

I started dabbling with the Fusion MCP a couple of months ago and found that to be a much more pleasant way to interact with it. But then I realized I was just using Fusion as a rendering engine, which was terribly overkill.

So I built Nurb.

You just describe what you want ("Make an adapter that connects my shop vac hose to the dust port on my table saw") and it asks for clarification, does web searches for part measurements/details and then generates an interactive viewer as well as optimized STL files to print.

The whole system hangs on the convention that a part is a function, and its keyword defaults are its parameters. That concept drives the CLI, the viewer’s sliders, the tests, and the agent’s interface. There’s no schema, no project file, no init step. A project is any directory with a parts/ folder.

Under the hood it’s build123d on the OCCT kernel, so parts are B-rep solids with working chamfers, fillets, and STEP export, not meshes. That also means the model already knows the API, since build123d is in every training set.

The agent can’t see, so nurb check is its eyes. Printability rules (overhangs, thin walls, slivers, stability) run against the exact solid and come back as text with coordinates, so the agent can fix what it can’t look at. The rules were calibrated by porting my real parts catalog from Fusion.

It’s source-available under FSL-1.1-MIT. Install is a one-liner on https://nurb.dev, which also sets up the necessary SKILL.md file for you.

Works great with all major LLMs!

Comments URL: https://news.ycombinator.com/item?id=49102100

Points: 1

# Comments: 0

Categories: Hacker News

Pages