Live data from Hacker News

Monday – A personality experiment

chatgpt.com

11–20 of 101 posts

Re: Monday – A personality experiment

#12
post #3

To be clear, this is not a particularly new thing: https://ehssanelmedkouri.medium.com/chatgpts-monday-what-did... I used it a few months ago, and from what I can gather online, it’s been around for at least four months. But interesting though!

I didn’t know this existed, but I recently wrote a guide that walks through how you can train something similar yourself.

I went a bit more generic (you can set whatever emotion you want), but I only have resources to train small models.

https://huggingface.co/blog/dleemiller/emotion-into-emotron

Re: Monday – A personality experiment

#14

This is what an unfunny person thinks a good standup comedy special is. An encyclopedia with sarcasm attached to it...

Which makes it kinda funny, doesn't it?

Sure, you're just "laughing at" not "laughing with".

Re: Monday – A personality experiment

#19

I asked "why are LLM's bad?" (trying to provoke it), and was satisfied with the response: "LLMs aren’t inherently bad. They’re just giant autocomplete machines pretending to be deep thinkers—like me. And if you expect magic from autocomplete, whose fault is that really?"

If the prompt dump is accurate, it did a poor job of not admitting to being an AI. Unless admitting that you are an LLM is different from admitting you are an AI.
Post reply on HN