Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: AskHN

patterns.app

Post reply on HN
Print view View original

51–60 of 139 posts

Re: Show HN: AskHN

#51

Post by tosemlep »

Did you also ingest dead comments to the corpus?

I would very much like to see the ghost of Terry pop up from time to time, to offer his wisdom and unique style of response.

Re: Show HN: AskHN

#52

Post by clark-kent »

btbuildem wrote: post #45

My own experiments made me think that the impact of finetuning is comparable to that of a molecule in a drop in a bucket. > “AskHN” is a GPT-3 bot I trained on a corpus of over 6.5 million Hacker News comments to represent the collective wisdom of the HN community in a single bot. I'm assuming you used the openai fine-tuning pathway to make a custom model? Have you tested the responses on vanilla GPT3 vs your custom…

From the article, they did not use fine-tuning. This is semantic search + GPT-3 to provide human-like answers.

Re: Show HN: AskHN

#53

Post by btbuildem »

agolio wrote: post #46
btbuildem wrote: post #44

Earlier quoted context omitted.

> “AskHN” is a GPT-3 bot I trained on a corpus of over 6.5 million Hacker News comments to represent the collective wisdom of the HN community in a single bot. First sentence of the first paragraph on OP's page EDIT: it's a bit misleading, further down they describe what looks like a semantic-search approach

Scroll a bit further down and you will see > 7. Put top matching content into a prompt and ask GPT-3 to summarize > 8. Return summary along with direct links to comments back to Discord user

Ah got it. Perhaps they should edit the intro then, it's misleading.

Re: Show HN: AskHN

#55

Post by cactusplant7374 »

dalmo3 wrote: post #54

This is nice! The official algolia search is useless. Otoh, did I miss something or is it only on discord?

I really like Algolia. I usually use it to see if a particular link has been submitted. Other times I use it to find relevant comments or posts.

Re: Show HN: AskHN

#57

Post by rpastuszak »

sebzim4500 wrote: post #23
have_faith wrote: post #11

It seems to write in the generic "style" of GPT, instead of in the style I would recognise as a HN poster. Is that because of something baked into how the training process works? It lacks a sort of casualness or air of superiority ;)

There was no training process, this is just running GPT with relevant HN comments as part of the prompt. If he wanted it to replicate that classic HN feel he would either have to extend the prompt with additional examples or, better yet, use finetuning. I guess he could also just randomly sprinkle in some terms like 'stochastic parrot' and find a way to shoehorn Tesla FSD into every conversation about AI.

Last year (pre the chatGPT bonanza) I was using GPT-3 to generate some content about attribution bias and the responses got much spicier once the prompt started including the typical HN poster lingo, like "10x developer":

https://sonnet.io/posts/emotive-conjugation/#:~:text=I%27m%2...

My conclusion was that you can use LLMs to automate and scale attribution bias.

We did it guys!

Re: Show HN: AskHN

#59

Post by gk1 »

clark-kent wrote: post #58

> 4. Index the embeddings in a database If Op is reading. I'm curious about the database you are using to store the embeddings. Pinecone, Weaviate ...?

From the article:

> The embeddings were then indexed with Pinecone.

Post reply on HN