Content
@
0 reply
0 recast
0 reaction
notdevin
@notdevin.eth
GPT o1, so far, sucks for code as far as I can tell. Itās insanely verbose and goes off the rails just as fast, but now for longer, than previous models. It has been awesome for conceptual brainstorming and system architecture. I much prefer Claude 3.5 or gpt 4, Iāll take 4o for boiler plate specifically Anyone else writing code having better experiences with o1 preview?
11 replies
4 recasts
27 reactions
Abubakarš©
@bigbenz
For me, when Iām engaging in technically-intense works I go with Claude Would got 4o give me equal amount of productivity?
1 reply
0 recast
1 reaction
notdevin
@notdevin.eth
Theyāre the same, I didnāt see anything that would have lead me to believe the hype of Claude being a game changed to the 4o GPT 4 & 4o = Claude 3.5
1 reply
0 recast
1 reaction
Abubakarš©
@bigbenz
š I admire how blunt you are, in your reviews I am actually been strongly persuaded by a friend to ditch Claude for gpt 4o like there was massive upgrade I wondered what he mightāve seen differently š¤
1 reply
0 recast
1 reaction
notdevin
@notdevin.eth
ššš¼ I will use gpt 4o when I need a complete reproduction of a file with N changes applied. Claude seems to be a bit more token efficient for its output which I like while building and donāt like while doing fine details that cause a couple changes across an entire file or boilerplate type work. With cursor you can just click click swap, so itās chill
1 reply
0 recast
1 reaction
Abubakarš©
@bigbenz
Hmm so apparently, they all got their specialties Are they outcome specific or user specific, like does it depend on the expected outcome or on the preference of the individual
1 reply
0 recast
1 reaction
