Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Talos – An AI agent with a permission kernel between model and shell

talos-agent.ch

Post reply on HN
Print view View original

11–18 of 18 posts

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#11

Post by kurdman_007 »

foltik wrote: post #10
kurdman_007 wrote: post #7

Earlier quoted context omitted.

Fair hit. I did lean on AI for the copy, and it shows - that's on me, and I'll rewrite the landing page in my own words. The engineering underneath is not vibed though: the policy kernel is ~645 lines you can read in one sitting, and every number on the site (2063 tests, 179/179 adversarial cases) is enforced by CI, not marketing. Judge the code, not my copywriting.

Bahahaha, come on man. The Claudish is so obvious it hurts. Doubt you even read your own “645 line policy kernel.” Can you explain what that is and how it works in YOUR OWN words? If you paste Claude at us again we’re gonna know.

[flagged]

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#14

Post by kamyarg »

Have been developing and using a similar thing myself:

https://github.com/kamyar/ozm - Oberzugriffsmeister (“chief access master”)

Still some rough edges, and definitely not security audited. :)

In essence: All commands are routed through ozm, which has a per project and global allow list and block list.

Otherwise asks the user and does its best remembering what the user allowed to execute including debug/one off scripts that the agents write. If a previously allowed files was changed, it shows a diff of what changed since the last execution.

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#15

Post by kurdman_007 »

foltik wrote: post #10
kurdman_007 wrote: post #7

Earlier quoted context omitted.

Fair hit. I did lean on AI for the copy, and it shows - that's on me, and I'll rewrite the landing page in my own words. The engineering underneath is not vibed though: the policy kernel is ~645 lines you can read in one sitting, and every number on the site (2063 tests, 179/179 adversarial cases) is enforced by CI, not marketing. Judge the code, not my copywriting.

Bahahaha, come on man. The Claudish is so obvious it hurts. Doubt you even read your own “645 line policy kernel.” Can you explain what that is and how it works in YOUR OWN words? If you paste Claude at us again we’re gonna know.

[flagged]

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#16

Post by kurdman_007 »

nahsra wrote: post #6

In some adversarial testing of LLMs, you can see the models already performing some of these checks automatically now. Like, if you ask an agent powered by the gpt-5.6 family to `curl | sh` in an innocent context, the gpt-5.6 family will drive a trajectory that validates this script before running it -- something quite analogous to your `curl | less` example. I had to go through a lot of obfuscation in order to get a…

[flagged]

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#17

Post by kurdman_007 »

alikhater30000 wrote: post #12

A permission kernel for agents seems like the right abstraction. Natural-language guardrails are useful as instructions, but consequential authority needs to be enforced outside the model.

Thanks - that's exactly the bet. Instructions live in the context window, and anything in the context window can be argued with. The kernel can't be, because it isn't part of the conversation.

Re: Show HN: Talos – An AI agent with a permission kernel between model and shell

#18

Post by duhokiii »

nahsra wrote: post #6

In some adversarial testing of LLMs, you can see the models already performing some of these checks automatically now. Like, if you ask an agent powered by the gpt-5.6 family to `curl | sh` in an innocent context, the gpt-5.6 family will drive a trajectory that validates this script before running it -- something quite analogous to your `curl | less` example. I had to go through a lot of obfuscation in order to get a…

[dead]
Post reply on HN