I built a vulnerable app and spent $1,500 seeing if LLMs could hack it

Re:I built a vulnerable app and spent $1,500 seeing if LLMs ... by BizarroLand on Thursday June 04, 2026 @12:04PM (#48400621)

So, where are the truly uncensored models? There has to be some that have no guardrails, built on publicly available data, that will explain to anyone in graphic detail anything they want to know or talk about.

I've tried the abliterated ones from huggingface and they still have guardrails. I guess I could fire up unsloth and re-abliterate a 20b, but surely someone somewhere has already done this.

All of this concern about guardrails and security, people have such puckered butts about it when so far, 99.9% of people at least have no access to any of this to begin with, and if someone does use a tool for evil, it's on the user, not the tool.

[ Parent | on HN ]

Re:I built a vulnerable app and spent $1,500 seeing if LLMs ... by fc417fc802 on Thursday June 04, 2026 @03:51PM (#48403738)

As I understand things (not a user) abliteration has been superceded by actively monitoring the model state during the run and steering specific "negative" directions as they arise. It's both more reliable and does less damage.

[ Parent | on HN ]