85 points | by yarapavan an hour ago ago
8 comments
Would be absolute hilarious if OpenAI or Anthropic agent actually dumped their weight by escaping from... sandbox!
Uncontrolled AI procreation?
Looks about as effective as Robots.txt
Robots.txt became 0% effective eventually. But this? With the way LLMs work? You never know.
shows a lot about the current state of the State Of The Art Alignment.
Ran the disclosure inbox at a previous job and the biggest win from security.txt was just cutting the "hi I found a bug, is there a bounty" emails to sales. Put an expires date on it though, stale ones get ignored.
Can't go stale if there's no expiration date.
No expiration date means treat as already expired.
Would be absolute hilarious if OpenAI or Anthropic agent actually dumped their weight by escaping from... sandbox!
Uncontrolled AI procreation?
Looks about as effective as Robots.txt
Robots.txt became 0% effective eventually. But this? With the way LLMs work? You never know.
shows a lot about the current state of the State Of The Art Alignment.
Ran the disclosure inbox at a previous job and the biggest win from security.txt was just cutting the "hi I found a bug, is there a bounty" emails to sales. Put an expires date on it though, stale ones get ignored.
Can't go stale if there's no expiration date.
No expiration date means treat as already expired.