michaelcjoseph pfp

michaelcjoseph

@michaelcjoseph

576 Following
982 Followers
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
I have to post on TBA to be eligible?
1 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Am I supposed to cast from the Farcaster app or TBA now? Asking for a friend.
1 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
In 10 years, using a browser instead of OpenAI agent (or equivalent) will be the same as coding in vim instead of an IDE.
0 reply
0 recast
1 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
It was not intuitive to me that this icon meant social. I get it after the fact, but I thought it was profile related at first.
2 replies
0 recast
3 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Getting tipped 1 USDC for your first post is a fun way to onboard users.
0 reply
0 recast
3 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
First post from TBA
0 reply
0 recast
1 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Any good resources or references on how to do this?
1 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Why does every vibe coder use @supabase and not Firebase? Never used the former so genuinely just curious.
5 replies
0 recast
8 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
I’m pretty pilled on specs being part of the codebase. Makes it way easier for LLMs to understand features and they’re way better at keeping the spec up to date as requirements change.
1 reply
0 recast
5 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Starting a new chat with an LLM for the same question is equivalent to restarting your computer. First, last, and best approach to fixing issues.
1 reply
2 recasts
16 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Posting this in the dev channel as well in case people are interested
0 reply
0 recast
1 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Latest @windsurf_ai vs @cursor_ai test, both using Claude 3.7 Sonnet: A race track. Prompt: Let's build a simple game where a user drives a car around an elliptical track using html, css, and javascript with an express server to run the page. They will use their keyboard with the keys "W,A,S,D" to control direction. Every lap registers a new lap time and you see your current lap time, latest lap time, and fastest lap time on the screen. Similarities: - Designs are identical - Keyboard functionality works - Both show instructions on the page Windsurf - Cannot turn unless you are moving - has track boundaries, but they are invisible - track boundaries are also very tight which means you have to be very precise with your driving - Timer doesn't work Cursor - Can turn even if you aren't moving (easier to drive) - No track boundaries - Precise marker to track start and end lap times which works, but because there are no track boundaries, it is easy to cheat Next test will be a mobile game built using Expo.
0 reply
0 recast
2 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Forgot to include the prompt I used: "Let's build the game flappy bird using html, css, and javascript with an express server to run the page"
0 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Follow up with the next test: Flappy Bird. Windsurf was significantly better than Cursor here. Windsurf: 90% success rate - Design was decent. Bird looked like a bird and pipes had some definition. - Collision detection was pretty good, but very conservative. If you were close to the pipe, it considered it game over. - Up and down motion was a little jumpy. Could have been smoother. - Functional scoring. Cursor: 50% of the way there - Design was very basic. The bird was just a ball and pipes were simply green cylinders. - The pipes don't even appear until about two seconds into the game. - Collision detection was completely broken. Even if you were to completely avoid a pipe, the game would end. - Scoring did not work. - Up and down motion and gravity in general was way smoother than Windsurf though.
1 reply
0 recast
2 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
claude 3.7 sonnet for both
0 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Ya Claude 3.7 Sonnet on both
0 reply
0 recast
2 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
I’ll keep posting updates as I move on to more complex games!
1 reply
0 recast
1 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Ohh Breakout is a good game to try next too.
0 reply
0 recast
0 reaction
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Been doing a little vibe coding of games for fun to compare Cursor and Windsurf. Been using the prompt, "Build x game in html, css, js using the next.js framework," and seeing how the output functions. Games tried so far: 1. Tic Tac Toe 2. Chess Both handled Tic Tac Toe with ease. No additional input from me needed. Chess was different. Both Cursor and Windsurf built a chess game. But using my sole prompt, Windsurf built out a fully featured chess game with move validation, check and checkmate status, move history, captured pieces, styling, etc. Cursor on the other hand, built the a barebones chess game and then outlined for me the next few milestones which would get me to feature parity with the Windsurf version. Once you worked through the milestones, the two versions were the same. Going to keep pushing forward here. Next up is Flappybird (will not use next.js for this one).
5 replies
6 recasts
28 reactions
michaelcjoseph pfp
michaelcjoseph
@michaelcjoseph
Took the day off to hang out with my son and nieces. I don’t know if there’s anything better than that.
0 reply
1 recast
2 reactions