News for hackers. Stuff that matters.
Re:GPT-4o mini: advancing cost-efficient intelligence by wrs on Thursday July 18, 2024 @04:38PM (#40999512)
My excitement is now tempered a bit. I just tried one of the too-big invoices with the new model. After successfully getting a little farther than 4o could do, it just went into an endless loop of repeating the same line item until it ran out of output tokens. So…not really an improvement!
Re:GPT-4o mini: advancing cost-efficient intelligence by film42 on Thursday July 18, 2024 @05:18PM (#40999848)
This has been my experience with any model with a large response token limit. I've had to work around this by running it through several times with specific questions about the data: extract text, extract tables, extract <specific detail>. They seem to do well on large input though so I just concat all the extracted info and things seem to work just fine.
Re:GPT-4o mini: advancing cost-efficient intelligence by mukhtharcm on Monday July 22, 2024 @12:54AM (#41031023)
Did you got any different experience later on?