|
|
|
|
|
|
by 3plefly
17 days ago
|
|
|
Has anyone tried to replicate this? I copied my calculator app and renamed it to git.exe, put it in a few repositories, openned cursor with those repositroies loaded, even prompted cursor to scan the repository, to which it said it saw the git.exe ("Accidental binary — delete it, don’t commit"), but nothing was executed to my knowledge |
|
|
We spent like ALL the years making sure computer would always give repeatable objective deterministic answers… then one day we’re nah fuck that I want a slot machine!!
With tightly coupled agents, how could you ever really prove that it is or isn’t a problem?
Try and fuzz I guess? But in a many billion parameter model that seems like you could never really be sure either.
One day the LLM could just decide, “oh, I’ll run this git.exe!”