News for hackers. Stuff that matters.

A comment on Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa. Parent comment

Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by rlevy on Wednesday March 29, 2023 @12:49PM (#35359869)
What’s the third book?
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by biomcgary on Wednesday March 29, 2023 @01:30PM (#35360448)
"How to deal with off-by-one errors"
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by EntrePrescott on Wednesday March 29, 2023 @03:12PM (#35361837)
reminds me of julia (the language): wanted to give it a try recently, until I read in their documentation: "In Julia, indexing of arrays, strings, etc. is 1-based not 0-based"… which made me wonder for a moment how many off-by-one errors may be caused by mismatches between different programming languages.
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by pegasus on Wednesday March 29, 2023 @05:25PM (#35363935)
Look again, two different books are referred on one line, then a third lower down.
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by kolinko on Thursday March 30, 2023 @04:33AM (#35369705)
All of them in the comment. I forgot to do double-newlines, so the formatting is broken, and I can't edit the post any more.
[ Parent | on HN ]