0xdesigner
@0xdesigner
o3 is best when giving codebase context and acting as an architect/planner claude 4 opus is absolutely ripping defined PRDs gemini 2.5 is best for specific small tasks gpt 4.5 is my favorite writer, gemini a close second o3/4o is the best image generator
9 replies
9 recasts
73 reactions
erica
@erica
gemini 2.5 pro is also the best at swift so far
1 reply
0 recast
5 reactions
Nick Smith
@iamnick.eth
I’ve been following your Cursor project flow and Claude 4 Sonnet *loves* rewriting the scratchpad and fking things up lol
1 reply
0 recast
0 reaction
tldr (tim reilly)
@tldr
cost and speed is another dimension too (when building a Wrapper product like we are)
0 reply
0 recast
1 reaction
David T Phung ⚛️⚡️🚀
@davidtphung
o3 + deep research for planning/ analyzing multiple csv files is 👌 the output of live formula cell spreadsheet is 💪 too
0 reply
0 recast
0 reaction
Shikha
@clumsycabutar
crazy how model literacy is becoming a legit skill now like knowing when to bring in o3 vs claude is the new “knowing which dev to assign” we’re basically prompt PMs at this point
0 reply
0 recast
1 reaction
Asha 🎩↑🔵
@asha
Pretty sure I'm not the only one who bookmarked this. Thanks for the insights 🙏
0 reply
0 recast
0 reaction
Steve (ozFather)
@pederzani.eth
I just realized GitHub bundles all these- is that kind of the typical setup right now to use a bundle package? I’m not a professional full stack dev but I like working setups that are familiar to those that are at least. Especially if it saves me from having more than 1 AI subscription service for editing and pre-research context crawling.
0 reply
0 recast
0 reaction
Joy
@cryptobaddie
Which one you use most?
0 reply
0 recast
0 reaction
@BestCryptoTwits
@bestcryptotwits
Claude is my favorite
0 reply
0 recast
0 reaction