Hacker News Reader

Useful link thanks. This approach is not cost effective though, I guess you're working on solution to optimize your cost. Fine tuning? Embedding?

View on HN

Honestly, I haven't worked on cost reduction yet. I have a backlog, but I haven't done anything from there.

One idea is to use other models to shorten text by throwing out meaningless words. I estimate this will reduce the length of the text (and thus the GPT cost) by 30%.

> One idea is to use other models to shorten text by throwing out meaningless words.

Does this mean GPT does not need coherent sentences to understand?

My feeling is that she understands much better than people do. If you understand a sentence from which some of the conjunction words have been taken out, she will understand 100%. And I think this will all be smoothed out on a transcript of 150,000 characters (that's the average size of a podcast).

Reply on news.ycombinator.com