News for hackers. Stuff that matters.
Re:Show HN: SiteGPT – Create ChatGPT-like chatbots trained o... by ashleynewman on Saturday April 01, 2023 @09:20PM (#35406100)
Disagree. I now defer to chatGPT instead of reading raw documentation. Even if it can hallucinate an answer it's still way faster and better for discoverability.
Re:Show HN: SiteGPT – Create ChatGPT-like chatbots trained o... by ElFitz on Sunday April 02, 2023 @03:26AM (#35408090)
Even better. When provided with your context (use case, models,…) it can adapt its answer to it.

Although that can also lead to hallucinations, it’s still quite wonderful.

Re:Show HN: SiteGPT – Create ChatGPT-like chatbots trained o... by tough on Sunday April 02, 2023 @10:24AM (#35410780)
Even better, just ask your stack

https://ask-your-stack.vercel.app/

(It uses official docs to provide answers with context)

Re:Show HN: SiteGPT – Create ChatGPT-like chatbots trained o... by ElFitz on Sunday April 02, 2023 @09:19PM (#35417366)
Quite nice, but by definition limited to the stacks it covers, isn’t it?
Re:Show HN: SiteGPT – Create ChatGPT-like chatbots trained o... by tough on Monday April 03, 2023 @06:37AM (#35421241)
It's open source, so you could certainly add any missing pieces, or even custom code which docs are not public, to your ask-your-stack* version.

At the end of the day with LangchainJS + LlamaIndex anything is possible