zlacker

[parent] [thread] 2 comments
1. famous+(OP)[view] [source] 2024-04-18 15:10:55
>Looks like such systems are good for generating marketing texts, but can not be used as diagnosticians by definition.

That's not true

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425828/

>Why did all these (slice of) world model approaches dead?

Because they don't work

replies(2): >>hello_+Gk >>eschat+OH1
◧
2. hello_+Gk[view] [source] 2024-04-18 17:02:37
>>famous+(OP)
Your article is a review of one language model (GPT-4) in diagnostics, while the original comment was an inquiry about world models.
◧
3. eschat+OH1[view] [source] 2024-04-19 05:15:17
>>famous+(OP)
How do you know?
[go to top]