@juli

If you don't know a topic well you're unlikely to build a good product and even less likely to vibecode one today. By contrast, if you know the product you want, the market is missing today, you can be very specific about the outcome and not rely on "AI guess work" that tends to be far off from good (no matter if you ask chatgpt/claude about investment help, crypto or non-crypto products) Either way helps a lot to add more context, discuss outcome & specs first. It'll be interesting if base models will be so good that this step is obsolete, if people go down rabbitholes or if the experts just advance faster than anyone else. ultimately - as usual - up to users to put in the work and get ahead.

1 reply

0 recast

6 reactions