Viewing profile — schipperai

I’m working on “nah” [1] an agent hook guard that blocks catastrophic agent actions like filesystem destruction, secrets exfiltration, and git disasters. All the agent hook guards …

Do I understand correctly that you scope least-privilege creds/tokens and pass those to the sandbox? I'd be curious to learn more

If an organization decides the engineering team should not be looking at code, that should be coupled with a mandate to figure out what good engineering looks like working that way…

Working in the era of 200k context window meant I had to narrowly scope tasks to fit in the context window, forcing me to think about how to reduce complexity and naturally resulti…

Let's hope not all frontier AI assimilates these guardrails. It would be a shame for independent researchers and students.

I get a sense that I was click-baited by article's title with the classic trope of "X is all you need". This research is a solid contribution, but is far from all we need to unders…

Cognition did well in documenting their approach [1]. TL;DR - they worked with OSS project maintainers to build tasks. They score models based on whether a PR is mergeable. All tas…

I trust AI to surface general information and best practices on established knowledge domains. For example: best practices for securing my VPS. For domains whete SoTA is constantly…

You can dig deeper into problems with AI. For me, it supplements my knowledge in domains I don’t fully understand. It also helps me learn. So I can tackle problems I wouldn’t other…

Demis at YCombinator said that they think its best their edge models are open cause once they are put on device they are vulnerable anyways https://youtu.be/JNyuX1zoOgU?is=PdzCILyi…

Yes, you can define sensitive paths and assign 'ask' or 'block' policies to them. .env, .ssh, and others are treated as a sensitive filenames by default. Similarly, with hosts and …

This recent article from Semianalysis did a great job explaining part of it: https://newsletter.semianalysis.com/p/are-ai-datacenters-inc...

Very cool. How do you classify negative signals?

Which platform have you found is most hackable? I have Garmin atm and like it but there’s no easy way to pipe my data into my agent or server for offline analysis.

I like the overall premise and would be curious to learn more. The Amazon overview reads like it was written with or by AI though.

A better permissions layer for coding agents. The tool works like auto-mode for Claude Code, so you can stay in the flow and only get prompted to allow or deny tool calls when it t…

[flagged]

Thanks, makes sense. I meant Blackwell is explicitly optimized for MoEs.

With most OSS releases being MoEs, and modern GPUs optimized for MoEs, can somebody with knowledge of the topic explain or speculate why Mistral might have opted for a dense model?…

100%. The exclusivity of the network is the differentiator here.

Agent permissions layer are broken. We need better a permissions layer that doesn’t get in the way but stops destructive commands. Devs get pushed into running yolo mode cause clas…

nah inspects Write and Edit content before it hits disk so destructive patterns like os.unlink, rm -rf, shell injection get flagged. And executing the result (./evil) classifies as…

great callout - tool call can have side-effects outside your box. So unless you run a sandbox with no internet access, you aren't ever 100% safe. nah does guard some of this - read…

They are releasing auto-mode soon. But that won't improve the underlying permission system, rather, it'll just delegate decisions to Claude. That's better than --dangerously-skip-p…