41–50 of 56 posts
ChatGPT was caught in blatant lie (if we can say such about language model), presented with 100% confidence (if we can say such about language model) multiple times.
https://www.uktech.news/news/nick-daloisios-news-aggregation...
Is there something like this but for pdfs?
Nice Easter egg: https://summate.it/https://summate.it
Nice Easter egg: https://summate.it/https://summate.it
Ah you found it! Didn't think anyone would try that. :D
It always puts a smile on my face when I come across clever ones like this, even though that's becoming rarer these days. I guess that's due to concerns about 'hidden code' in commercial codebases, which third-party license holders might be skeptical about.
Earlier quoted context omitted.
we have done just that, check it out https://news.ycombinator.com/item?id=33748363
I did too! See a link elsewhere in this thread.
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
Autosummarized HN:
The article discusses how a loss of epigenetic information causes yeast cells to lose their identity and age, and how this process can be reversed by OSK-mediated rejuvenation.
- Aging is caused by the loss of epigenetic information, leading to a variety of age-related diseases and processes.
- Epigenetic regulation of aging is affected by environmental inputs, including DNA damage and changes in the TGFbeta signaling pathway.
- Studies in mammals, such as mice, have revealed a wide range of epigenetic changes associated with aging, including increased transcriptional stress, changes in chromatin structure, and increased Wnt signaling.Earlier quoted context omitted.
Not too hard, just "map reduce" it: Have GPT-3 summarize each section of the article, and then have it summarize the summaries.
I've tried it, it doesn't really work that well. There are other much more convoluted approaches that have promise (embedding searches is one)
Earlier quoted context omitted.
I've tried it, it doesn't really work that well. There are other much more convoluted approaches that have promise (embedding searches is one)
Could you expand on this? Is the idea to embed paragraphs (or some other arbitrary subsection) of text, and then semantic search for the most relevant paragraphs, and then only summarize them?
The hardest part is dealing with GPT token limits. You can't summarize long form text, where it's most needed.
I didn't try, but it seems GPT-Index and LangChain use techniques to get around prompting length limits?