Content pfp
Content
@
0 reply
0 recast
0 reaction

notdevin  pfp
notdevin
@notdevin.eth
GPT o1, so far, sucks for code as far as I can tell. It’s 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, I’ll take 4o for boiler plate specifically Anyone else writing code having better experiences with o1 preview?
11 replies
4 recasts
27 reactions

Abubakar🎩 pfp
Abubakar🎩
@bigbenz
For me, when I’m 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  pfp
notdevin
@notdevin.eth
They’re the same, I didn’t 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

Abubakar🎩 pfp
Abubakar🎩
@bigbenz
😅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 might’ve seen differently 🤔
1 reply
0 recast
1 reaction

notdevin  pfp
notdevin
@notdevin.eth
😂🙏🏼 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 don’t 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 it’s chill
1 reply
0 recast
1 reaction

Abubakar🎩 pfp
Abubakar🎩
@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

notdevin  pfp
notdevin
@notdevin.eth
I think I’m not sure on that one. I know how I use prompts and based on that I get fairly consistent expectations of what will come out. A totally different prompt style may yield results altogether different than my experience, though I imagine the difference may need to be rather dramatic
1 reply
0 recast
1 reaction

Abubakar🎩 pfp
Abubakar🎩
@bigbenz
Oh that’s true, it should take a much dramatic prompt to give a totally different outcome You made mention of cursor, tbh I don’t use that, I often think it’s for designers only, is it ?
1 reply
0 recast
1 reaction