logoalt Hacker News

qarl2last Monday at 3:10 PM1 replyview on HN

You did not hit max depth - you hit a timer designed to prevent rage posting.

My question stands - if you accept that LLM harnesses are designed to allow the building and testing of executables - how do you imagine you can prevent the building and running of executables?

Respectfully.


Replies

ethbr1yesterday at 3:23 PM

Going from "build and running executables" to that needing to be done on the same system and under control of the LLM is a large leap.

Separation of duties and ephemerality are well-known security mechanisms that many harnesses jump right over in the pursuit of easier UX.

Mingling permissions + trusting vibe-coded security boundaries in the harness itself (developed by folks whose appetite for risk would make even an 00s front-end developer blush) is rolling a handful of dice all at once.

But fundamentally, this is a disagreement between two risk appetites who will never agree: {it works most of the time} vs {it's guaranteed to never fail}

show 1 reply