Malware uses LLMs to rank victims by how much they're worth

Re:Malware uses LLMs to rank victims by how much they're worth by thisisauserid on Saturday October 31, 2026 @12:57PM (#50317852)

At priority ranking? It's less accurate, slower, and more expensive than every other purpose-built tool.

[ Parent | on HN ]

Re:Malware uses LLMs to rank victims by how much they're worth by ctxc on Saturday October 31, 2026 @01:15PM (#50318013)

You're technically right, which is why I say "good enough".

It's a good strat imo - start simple and get it working with LLMs asap, then you can add heuristics etc based on the data you have and improve with that benchmark

[ Parent | on HN ]

Re:Malware uses LLMs to rank victims by how much they're worth by pixl97 on Saturday October 31, 2026 @01:00PM (#50317881)

Ah yes, I see the malware authors buying subscriptions to the appropriate software to do that.

[ Parent | on HN ]

Re:Malware uses LLMs to rank victims by how much they're worth by thisisauserid on Saturday October 31, 2026 @01:30PM (#50318139)

All those tools are FOSS.

[ Parent | on HN ]

Re:Malware uses LLMs to rank victims by how much they're worth by anigbrowl on Saturday October 31, 2026 @04:29PM (#50319837)

I'm no genius, but I've managed to set up my agents to prefer writing a small python script or whatever to do repetitive/iterative tasks that my language model 'knows' it's not good or efficient at.

[ Parent | on HN ]