Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ...
by stavros on Monday December 30, 2024 @09:20AM
(#42549468)
Where are you getting that Deepseek is at the level of o1? In my experience, it's not even as good as Claude.
[ Parent
| on HN ]
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ...
by esafak on Monday December 30, 2024 @11:40AM
(#42550877)
Even v3?
edit: Fair enough. I'm fishing for opinions too.
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ...
by stavros on Monday December 30, 2024 @12:08PM
(#42551188)
My testing has been very limited, so I don't want to opine too much. If anyone has a differing opinion based on more testing, please share, I'm interested!
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ...
by tomjuggler on Monday December 30, 2024 @01:41PM
(#42552220)
So I've been using Deepseek for 3 months with Aider coding assistant. Look up the "Aider LLM leaderboard" for proper test results if you like, in my experience the Deepseek V3 is just as good as Claude at less than 1/10th the price. I can't speak about o1 it is just too expensive to be worth it
OpenAI is going to be beaten on price, wait and see.
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ...
by stavros on Monday December 30, 2024 @01:43PM
(#42552231)
Did Aider integrate v3 in its benchmarks? I checked yesterday and I didn't see it...
EDIT: Oh it did, wow, and it's better than Claude! Fantastic, this is great news, thank you!