airic.serveo.net

AI

fine-tuned chat model

SHOW HN2023

airic.serveo.net

I trained a 65B LLM on my texts to talk to myself (details inside)

airic.serveo.net

#llama#lora fine-tuning#chatbot#oobabooga

13points
7comments
#2,112of 3,109 in 2023
Top 68%of 2023 by points

How HN took it

QuietFewer than 5 comments about the project

2 positive, 1 neutral or asking, 0 mixed, 1 critical, out of 4 comments about the project.

Performance: 2 for, 0 againstPrivacy: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Entertaining and funny responses

    From 2 comments
    • Cool. But please tell me that your childhood phone number wasn't 708-642-9XXX (censored in case it's real) because it just told me that "fact"... and we were chatting about…
      coreyp_1 on HN
    • According to this, your boss Matt Cain is the most annoying person you know. This would be a much more exciting chat if it hadn’t been scrubbed haha
      clarkmcc on HN

Objections

  • Might leak secrets or make up personal details

    From 1 comment
    • It is a cool app but it might spill secrets? It told me some things like someone’s name who you know, but it could be making it up.
      quickthrower2 on HN

Requests

  • Pre-generated quick reply answers from real chats

    From 1 comment
    • This is so interesting. I've been wanting to do this, not to chat, but to generate coherent answers to real chats - like pre-baked answers to quickly reply. Looks pretty…
      kinduff on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/36815443)