Live data from Hacker News

Show HN: Summate.it – Quickly summarize web articles with OpenAI

summate.it

1–10 of 56 posts

Re: Show HN: Summate.it – Quickly summarize web articles with OpenAI

#7

The hardest part is dealing with GPT token limits. You can't summarize long form text, where it's most needed.

Agreed, you can try sending it in chunks but then you lose context. Perhaps the ChatGPT based API will help if they expose the conversational memory as a feature.

Maybe OP has figured out a method with the current API?

Re: Show HN: Summate.it – Quickly summarize web articles with OpenAI

#8

The hardest part is dealing with GPT token limits. You can't summarize long form text, where it's most needed.

Agreed, you can try sending it in chunks but then you lose context. Perhaps the ChatGPT based API will help if they expose the conversational memory as a feature. Maybe OP has figured out a method with the current API?

I saw in another thread that people were working around this by asking for a summary of sections and then combining the summaries and asking for a joint summary.

Kind of like map reducing the articles.

Re: Show HN: Summate.it – Quickly summarize web articles with OpenAI

#9

The hardest part is dealing with GPT token limits. You can't summarize long form text, where it's most needed.

Agreed, you can try sending it in chunks but then you lose context. Perhaps the ChatGPT based API will help if they expose the conversational memory as a feature. Maybe OP has figured out a method with the current API?

This is an issue. I haven't experimented to see if there are workarounds, so the service currently checks the length of the article text and if it's very long, it will send a portion, otherwise we'll exceed the token limit. There's a note on the front page about it: "Limitations: The OpenAI API does not allow submission of large texts, so summarization may only be based on a portion of the whole article."

Re: Show HN: Summate.it – Quickly summarize web articles with OpenAI

#10

Earlier quoted context omitted.

Agreed, you can try sending it in chunks but then you lose context. Perhaps the ChatGPT based API will help if they expose the conversational memory as a feature. Maybe OP has figured out a method with the current API?

I saw in another thread that people were working around this by asking for a summary of sections and then combining the summaries and asking for a joint summary. Kind of like map reducing the articles.

O believe this is how GPT-Index attempts to bypass prompt length limitations.
Post reply on HN