Gregory's Server@theogrin @kkolakowski @alyssa LLMs don't necessarily need to generate stuff
There are signs of promise for LLMs that avoid hallucination by paraphrasing and permutating instead.
I recommend checking out perplexity.ai
LLMs are also quite helpful for automation; the base training data is just to get the relations right in the first place, then constraints, checks, temperature, and human validation can help vet things out
@theogrin @kkolakowski @alyssa
Base LLMs like GPT are useless to your average Joe but great for developers (i.e., you need to know prompt engineering and AI model tooling); ChatGPT is fun for conversations and the public but useless otherwise, and Perplexity is only good for taking multiple raw articles and quoting them directly