.@sama says the advice to pick one thing to build and pour all your focus into it no longer applies.
"The canonical advice that was correct two years ago was, 'Pick one, and put all your effort into it, because you can't build all 30 things.'"
"You can now build all 30 things. And you can get people to use them all. And you can work more on the ones that work."
"So I think this mindset of lots of ideas, quick feedback, and being open to a lot of things not working is great for this new era for how people build."
My buddy @jessems ask me for help to create a promo video for one of his apps.
This what I got.
Using Gemini 3.8 TTS for voice.
Post a link to your product and I will make one for you later today on my break time.π
Lets go!
I'm betting that this is wrong.
Building it used to be the moat. Not building it is easy.
So build harder things (that people will still want). There's your moat.
distribution is the only moat left so you better use all your product to cross-promote eachother
this always work for me before and seems to be even more important now
Don't quite understand people saying they don't use any type of planning/plan mode.
Even with models as good as Astra and Opus 5.5, without using something like @mattpocockuk's /grill-me beforehand, there's just too many ways for the model to solve the wrong problem.
This has never been more true. The opportunity cost of endless planning and contemplation just went way up. Agents allow you to just try vastly more stuff, so let them, and you'll learn way more, way faster.