Hacker News new | ask | show | jobs
by sixstringtheory 1233 days ago
Just had a dinner conversation where ChatGPT was characterized as automated plagiarism, and then I thought wouldn’t it be cool to get like a set of BibTex entries for all the sources whose content were combined to synthesize an output.

Not sure that’s possible, and even if so, that it would be any kind of reasonable or manageable size whatsoever.

2 comments

You'd see hallucination in the citations too. Ultimately, you can't get away from having to manually verify everything that an LLM outputs.
I run the cheaper self hostable OpenAI alternative https://text-generator.io I've been working on automating this manual verification of everything, with a few components we already have like a search engine and an edit API we can both detect and correct most of these errors to at least be reflective of what a reliable source says like Wikipedia, still a lot of reasoning, logic and math issues will remain, but there's a big step up coming soon in factual generation
| what a reliable source says like Wikipedia

oh dear me

perplexity.ai does this