Comment on Google AI chatbot responds with a threatening message: "Human … Please die."
TranquilTurbulence@lemmy.zip 3 days ago
Would be really interesting to know what kind of conversation preceded that line. What does it take to push an LLM off the edge like that.
JackbyDev@programming.dev 2 days ago
TranquilTurbulence@lemmy.zip 2 days ago
Thanks. Seems like a really freaky situation. Must be something with the training data. My guess is, this LLM was trained with all the creepy hostility found on Twitter.
JackbyDev@programming.dev 2 days ago
I chalk it up to either a working clock being weird every now and then or prompt engineers trolling.
otter@lemmy.ca 3 days ago
None that I can see, it looks like they were pasting in questions from their school assignments. There is a link to the chat, and I included some more thoughts in my other comment
TranquilTurbulence@lemmy.zip 3 days ago
Oh, there it is. I just clicked the first link, they didn’t like my privacy settings, so I just said nope and turned around. Didn’t even notice the link to the actual chat.
Anyway, that creepy response really came out of nowhere. Or did it?
What if the training data really does contain hostile and messed up stuff like this? Probably does, because these LLMs have eaten everything the internet has to offer, which isn’t exactly a healthy diet for a developing neural network.
thingsiplay@beehaw.org 3 days ago
Usually LLMs for the public are sanitized and censored, to prevent lot of creepy stuff. But no system is perfect. Some random state can cause random answers that makes no sense, if triggered. Microsofts Ai attempts, Google’s previous Ai’s, ChatGPT and other LLMs all had their fair share of problems. They will probably add some more guard rails after this public disaster; until next problem happens. There are dedicated users who try to force this kind of stuff, just like hacker trying to hack websites (as an analogy).
Bougie_Birdie@lemmy.blahaj.zone 3 days ago
With the sheer volume of training data required, I have a hard time believing that the data sanitation is high quality.
If I had to guess, it’s largely filtered through scripts, and not thoroughly vetted by humans. So data sanitation might look for the removal of slurs and profanity, but wouldn’t have a way to find misinformation or a request that the reader stops existing.
TranquilTurbulence@lemmy.zip 3 days ago
Stuff like this should help with that. If the AI can evaluate the response before spitting it out, that could improve the quality a lot.