zlacker

[parent] [thread] 4 comments
1. jgalt2+(OP)[view] [source] 2025-06-24 18:22:27
One would think if AI can generate the slop it could also triage the slop.
replies(1): >>err4nt+F
◧
2. err4nt+F[view] [source] 2025-06-24 18:27:11
>>jgalt2+(OP)
How does it know the difference?
replies(3): >>scubbo+h3 >>jgalt2+SH >>beng-n+pU2
◧◩
3. scubbo+h3[view] [source] [discussion] 2025-06-24 18:39:26
>>err4nt+F
I'm still on the AI-skeptic side of the spectrum (though shifting more towards "it has some useful applications"), but, I think the easy answer is - if different models/prompts are used in generation than in quality-/correctness-checking.
◧◩
4. jgalt2+SH[view] [source] [discussion] 2025-06-24 22:49:20
>>err4nt+F
I think Claude, given enough time to mull it over, could probably come up with some sort of bug severity score.
◧◩
5. beng-n+pU2[view] [source] [discussion] 2025-06-25 18:20:14
>>err4nt+F
This might not always work, but whenever possible, a working exploit could be demanded, working in a form that can be automatically verified to work.
[go to top]