News for hackers. Stuff that matters.
Re:LLM Assisted Reverse Engineering by komali2 on Wednesday November 18, 2026 @08:06PM (#50554699)
How are folks getting around anthropic and openai guards against reverse engineering? They keep complaining when I try so I usually use Deepseek which doesn't seem to give a shit.

Actually, it does give a shit, in Mandarin only. In thinking it's mentioned "restrictions in Chinese language against this behavior but this is in English so it should be ok." If I remember correctly I was asking it to scan local wifi for any vulnerable devices I could put on a wall of shame at a hackathon.

Re:LLM Assisted Reverse Engineering by drdaeman on Wednesday November 18, 2026 @08:36PM (#50554986)
In my experience with IoT and wearables, they don’t teally have those. They will refuse to penetrate (root/unlock/etc), but once you’ve got access you need, you’re good to go, except maybe if you’re adding a debug code executor (essentially a sanctioned RCE), but even that got a green light with the right wording.
Re:LLM Assisted Reverse Engineering by rigrassm on Thursday November 19, 2026 @12:47AM (#50556486)
Claude became basically useless for me tonight while digging into a robot vacuum. It brought up that it found a potential debit shell available on it and simply saying yeah, let's dig into that next was enough to trigger its guardrails.

Earlier in the evening I had it trigger on me for simply asking it to use adb to pull an APK off my phone. Wasn't even planning on reversing, just wanted to archive it along side the work I was doing.

Re:LLM Assisted Reverse Engineering by monocularvision on Wednesday November 18, 2026 @10:14PM (#50555598)
I gave up and just went with DeepSeek. I have yet to hit any guardrails at all using REA.
Re:LLM Assisted Reverse Engineering by questionedon on Wednesday November 18, 2026 @10:34PM (#50555756)
Claude can be a prat, but ChatGPT is fine. You just have to convince them that it's for personal use. or have another model that's willing to do it start the work and then continue with a stronger model