News for hackers. Stuff that matters.
Re:Fuck Your AI Safeguards by neographikal on Thursday November 19, 2026 @02:32PM (#50565055)
Ik was investigating the java vulnerabilities this week. Just trying to get an overview of what versions were affected and if there were exploits already. Claude opus plainly refused, unbelievable. It was in the we interface, no offensive stuff, just investigating.

Total frustration while the work pressure was already high. Sol and astra thankfully complied and were very useful. Saved me hours compared to doing it by hand during log4j

Re:Fuck Your AI Safeguards by collinvandyck76 on Thursday November 19, 2026 @02:41PM (#50565195)
I hit the same thing. Session got flagged while I was trying to figure out what was vulnerable. Hilariously, I reframed it as "let's find all of the paths from app code that can arrive at the base64 decoder" which didn't seem to trigger any of the same guards.
Re:Fuck Your AI Safeguards by neographikal on Thursday November 19, 2026 @03:21PM (#50565785)
Yeah you can fool it, and I wasn't even touching code. Just doing online research. And I didn't really have the time. Needed to decide if we were going full log4j in a large university landscape or if we could take a more nuanced approach.

Was a case of don't have the time or the patience to fight the model: just work damnit...

Re:Fuck Your AI Safeguards by BeetleB on Thursday November 19, 2026 @04:38PM (#50566804)
As I said a few days ago - these are a joke because sometimes they are ridiculously easy to subert:

I was running something at work that involved an LLM, and kept getting safety refusals. The weird thing was that when I went to our in-house chatbot, set the model to the same one the program was using, entered the same text, it happily answered.

I spent quite a while trying to figure out why my program was being refused. Was I doing something wrong?

No - the chatbot was doing something "right". You see, the chatbot had some tools it injected into the prompt (current time, etc). These tools had no relevance to my query.

So I went back to my program and injected the same tools. Suddenly my request was very safe.

The phrase "security theater" was invented for stuff like this.

Re:Fuck Your AI Safeguards by nedt on Friday November 20, 2026 @08:22AM (#50574292)
Very similar here. Claude Opus was fetching relevant pages and came across one explaining what is exploitable. Got flagged for cyber security reasons. I then asked for the URL and copy and pasted the page content in a prompt. Suddenly it was fine.