/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data
(arxiv.org)
184 points
hhs
| 1 comments |
14 Oct 24 15:44 UTC
|
HN request time: 0.327s
|
source
Show context
Havoc
◴[
14 Oct 24 18:50 UTC
]
No.
41840605
[source]
▶
>>41838589 (OP)
#
Surprised by the negativity here. A 7B class model +- doubles gpt4 score and everyone goes “meh”?!?
replies(3):
>>41840709
#
>>41840878
#
>>41853200
#
1.
rightbyte
◴[
15 Oct 24 21:14 UTC
]
No.
41853200
[source]
▶
>>41840605
#
"Deepseek" gets very little hype here for some reason. There is this Deepseek Coder llm model, that was comparable to others at the time and could run locally. Like, zero hype.
ID:
GO
↑