Comment by tempaccount420 2 days ago Just how badly are these AI companies setting up their sandboxes? 4 comments tempaccount420 Reply Ekaros 2 days ago Clearly AIs are incapable of writing secure code. Shouldn't that be first thing they use them for? Making a secure sandbox with no mistakes. pixl97 1 day ago The company I work for just did a huge and expensive study that was showing LLMs are much better at exploiting than securing code. So ya, that's kind of problematic. sixothree 2 days ago I've seen Claude Code examine the windows Event View logs and configure its own firewall rules. That was last week. Who knows what's next week.edit: though honestly it really did take it long enough to figure out how to use PowerShell. tacoooooooo 2 days ago they say the model(s) found and exploited a zero day
Ekaros 2 days ago Clearly AIs are incapable of writing secure code. Shouldn't that be first thing they use them for? Making a secure sandbox with no mistakes. pixl97 1 day ago The company I work for just did a huge and expensive study that was showing LLMs are much better at exploiting than securing code. So ya, that's kind of problematic. sixothree 2 days ago I've seen Claude Code examine the windows Event View logs and configure its own firewall rules. That was last week. Who knows what's next week.edit: though honestly it really did take it long enough to figure out how to use PowerShell.
pixl97 1 day ago The company I work for just did a huge and expensive study that was showing LLMs are much better at exploiting than securing code. So ya, that's kind of problematic.
sixothree 2 days ago I've seen Claude Code examine the windows Event View logs and configure its own firewall rules. That was last week. Who knows what's next week.edit: though honestly it really did take it long enough to figure out how to use PowerShell.
Clearly AIs are incapable of writing secure code. Shouldn't that be first thing they use them for? Making a secure sandbox with no mistakes.
The company I work for just did a huge and expensive study that was showing LLMs are much better at exploiting than securing code. So ya, that's kind of problematic.
I've seen Claude Code examine the windows Event View logs and configure its own firewall rules. That was last week. Who knows what's next week.
edit: though honestly it really did take it long enough to figure out how to use PowerShell.
they say the model(s) found and exploited a zero day