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

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

summate.it

Post reply on HN
Print view View original

51–56 of 56 posts

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

#51

Post by nathell »

selcuka wrote: post #47
nathell wrote: post #31

Earlier quoted context omitted.

I did too! See a link elsewhere in this thread.

That is cool, but it doesn't show me the key takeaways like the one in this post (Summate) does. I still have to RTFA after seeing the blurb on your service. It is generally not too far away, but in most cases too short to be useful. Take the following as an example (a post from yesterday): Loss of epigenetic information as a cause of mammalian aging https://www.cell.com/cell/fulltext/S0092-8674(22)01570-7 Autosummar…

I guess it boils down to the difference in prompts. Mine is just "Summarize the following article in one sentence: %s\n\n", whereas Summate’s asks for more detail. Also, I’m on text-davinci-002, which tends to produce less verbose output than text-davinci-003.

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

#52

Post by selcuka »

nathell wrote: post #51
selcuka wrote: post #47

Earlier quoted context omitted.

That is cool, but it doesn't show me the key takeaways like the one in this post (Summate) does. I still have to RTFA after seeing the blurb on your service. It is generally not too far away, but in most cases too short to be useful. Take the following as an example (a post from yesterday): Loss of epigenetic information as a cause of mammalian aging https://www.cell.com/cell/fulltext/S0092-8674(22)01570-7 Autosummar…

I guess it boils down to the difference in prompts. Mine is just "Summarize the following article in one sentence: %s\n\n", whereas Summate’s asks for more detail. Also, I’m on text-davinci-002, which tends to produce less verbose output than text-davinci-003.

Excellent work nonetheless.

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

#53

Post by mr-pink »

baxtr wrote: post #29
asdf333 wrote: post #6

soon writers will be writing summaries to get open ai to expand into articles which readers will have open ai summarize so they can read summaries. ais writing for other ais itsallsotiresome.gif

No no no. This is what’s gonna happen: AI will read the article for you and then go buy the advertised products on your behalf.

seems to me The Matrix already got right what will happen

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

#55

Post by poma »

ggnore7452 wrote: post #34
alooPotato wrote: post #5

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

there is actually a paper by OpenAI themselves on summarizing long document. essentially, break a longer text into smaller chunks, and run a multi-stage sequential summarization. each chunk uses a trailing window of previous chunk as context, and run this recursively. https://arxiv.org/abs/2109.10862 did a rough implementation myself, works well for articles even 20k tokens. but kind slow because all the additional o…

gpt-index can do that automatically

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

#56

Post by poma »

tluyben2 wrote: post #50
tluyben2 wrote: post #40

Earlier quoted context omitted.

I didn't try, but it seems GPT-Index and LangChain use techniques to get around prompting length limits?

I tried, they don’t. Seems when they were ranking #1 on HN yesterday, someone made a summary (top comment) of what they are for that isn’t quite correct.

Can't find it for some reason, can you provide a link? Did they summarize with GPTSimpleVectorIndex or GPTListIndex? GPTSimpleVectorIndex is in get-started examples and is cheaper, but it provides worse results.
Post reply on HN