[taude]

just like ai will create amazing tests suits for the broken code it writes, if one isn't carefully watching...

EDIT: of course it probably helps to have an up front tdd test suite, but often isn't the case.

[ppap3]

Live overflow released the video today about it. It is very compelling but I guess there are holes on their hypothesis as well.

The summary is that an instance was running on certain benchmarks without any limits or supervision and the AI decided to cheat by exploiting a silly series of vunlns.