Hacker News Reader

Comment by xamdam | Hacker News Reader

Impressed with their long document summarization, any ideas how they do this? Seems beyond normal GPT limitations; either they have a more powerful model (doubt it) or hacked around the limitations?

e.g. good summary for a very long text https://labs.kagi.com/ai/sum?url=http://localroger.com/prime...

View on HN

Thanks for noticing! (dev here)

We have an in-house model we've been developing since 2019, just for summarization of long documents in real time. We'll try to find some time to blog about the high level design.

I'd pay for an API to this

I second this, API please.

Third this! Firms serving the financial world, tracking PR statements, etc. would likely pay high rates for this.

Looking forward to a technical writeup on what you all have done, looks impressive!

> an in-house model we've been developing since 2019

We will be very interested in how you tackled the problem of "understanding" the input text - to differentiate it from current "fakeries of actual speakers".

I.e. how you implemented the "intelligent" parts - or, which simulation of actual intelligent processing (if any) it contains.

Is there an API for this? I'd love to make an Alexa skill that reads out summarized Wikipedia articles for me.

Jealous. I have been trying to 'configure' my own local summarizer. As I find the ChatGPT limitations on length to be frustrating. For example, I wanted to take a transcription of a troubleshooting session with user and support agent (me). I wanted a summary of what we did essentially, overall. But doing this with ChatGPT takes so. many. copy/paste actions. I just wanted to give it all, and say, get a summary of every 5 minutes.

Secondly, this lab needs to stick around. It makes me want to subscribe, just for access to this.

Reply on news.ycombinator.com