Content
@
https://warpcast.com/~/channel/aichannel
0 reply
0 recast
0 reaction
Dan Romero
@dwr.eth
Question for devs: is Claude still the best model for actual coding? If so, by how much?
22 replies
19 recasts
117 reactions
Ben Adamsky 💭
@ba
I've tried r1, o1, and o3 and the answer is still clearly yes Claude is no longer my go to for big architectural discussions, but it's the best at understanding a codebase and delivering a clear solve with minimal refactoring. Oh, and it's still blazing fast in comparison. So no for high level, yes for code
2 replies
1 recast
25 reactions
basement5k.⌐◨-◨ 🟡
@basement5k.eth
What are your thoughts on using Vercel's v0?
1 reply
0 recast
0 reaction
Ben Adamsky 💭
@ba
Great for prototyping, not great for solving real problems
1 reply
1 recast
1 reaction
basement5k.⌐◨-◨ 🟡
@basement5k.eth
yeah thats totally fair. Im a new coder - so its great for me to test layouts. but with little coding knowledge It is very difficult to transfer a great idea I have from v0 to actual cursor to go live
1 reply
0 recast
1 reaction
Ben Adamsky 💭
@ba
Yeah v0 is great for that Once you're further along in web app development you begin to have specific preferences that these boilerplate AI generators can't predict Easiest way to overcome that is to import your entire codebase into cursor and use a model that can understand the context before writing any code
1 reply
1 recast
1 reaction
basement5k.⌐◨-◨ 🟡
@basement5k.eth
true. Ive tried doing that, but when I do, I get an obnoxious amount of errors. My assumption is because all of the assets/references within the code are stored on v0s server and not my machine
1 reply
0 recast
1 reaction
