Soon we’ll find delivery robots trying to pull some amazing stunts, all thanks to the sacrifices of some daring Pokemon Go players. Good times ahead 🍿

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.

They could just run the whole dataset through sentiment analysis and delete the parts that get categorized as negative, hostile or messed up.

Twitter is another possibility. The LLM could have learned how to write like a bubbling barrel of radioactive toxic waste, and then just applied those lessons in longer format.

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.

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.

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. Did the student pull a DAN or something?

It would make sense to include matching images in the search results and other engagement driven recommendations. There are quite a few screenshots too, so if the search can only handle text, it’s going to completely miss a pretty large category.

It’s probably going to be a rare collectible in about 50 years. Right now, it’s a high risk investment.