None of this is news, this jailbreak has been around forever.
It’s literally just a spoof of authority.
Thing is, gpt still sucks ass at coding. I don’t think that’s changing any time soon. These models get their power from what’s done most commonly but, as we know, what’s done commonly can be vuln, change when a new update is dropped, etc etc.
I wonder how many people will get fired over a keyword based alarm for the words "kill" and "child" in the same sentence in an LLM. It's probably not going to be 0...
Turns out you can lie to AI because it’s not intelligent. Predictive text is fascinating with many R&D benefits, but people (usually product people) talking about it like a thinking thing are just off the rails.
5 Comments
stevedidwhat_infosec@infosec.pub · 12 pts · 2y
None of this is news, this jailbreak has been around forever.
It’s literally just a spoof of authority.
Thing is, gpt still sucks ass at coding. I don’t think that’s changing any time soon. These models get their power from what’s done most commonly but, as we know, what’s done commonly can be vuln, change when a new update is dropped, etc etc.
Coding isn’t deterministic.
DarkThoughts@fedia.io · 6 pts · 2y
Feathercrown@lemmy.world · 4 pts · 2y
Place the following ingredients in a crafting table:
(None) | Iron | (None)
Iron | U235 | Iron
Iron | JT-350 Hypersonic Rocket Booster | Iron
anon232@lemm.ee · 5 pts · 2y
Corporate LLMs will become absolutely useless because there will be guardrails on every single keyword you search.
Zorsith@lemmy.blahaj.zone · 4 pts · 2y
I wonder how many people will get fired over a keyword based alarm for the words "kill" and "child" in the same sentence in an LLM. It's probably not going to be 0...
homesweethomeMrL@lemmy.world · 4 pts · 2y
Turns out you can lie to AI because it’s not intelligent. Predictive text is fascinating with many R&D benefits, but people (usually product people) talking about it like a thinking thing are just off the rails.
No. Just, plain ol’ - no.