Last Notes
https://nostpic.com/media/5e5fc1434c928bcdcba6f801859d5238341093291980fd36e33b7416393d5a2c/3335b552594a1eb3be6300fd345df708fca6e6f7d32757e095491585733cdc7e.webp
#boobstr got bigger in size
everyone wanna SELL own CODE
messaging unification NOT benefit anyone
I saw this on Twitter. Great work!
https://youtu.be/QFgcqB8-AxE?is=8Lcwyx3_4CWegbkG
https://www.brevo.com/ got compromised
it’s anything but sad! i’m over the moon. anyone who can accurately articulate what they want (and yes, that’s still a hard skill to be good at) can build anything. it’s a beautiful time to be alive.
the difference between a few months ago and now is significant. i wouldn’t have said this same thing even 6 months ago.
It's just customer service. I have them my seed phrase so that they could help my. Nothing to worry about.
gm. be careful out there folks.
https://blossom.primal.net/4846a7f7f13694d6ac55669831136ac079191b1912ce4f71c6f4c6229959c82d.jpg
My experience is similar. Even top models like GPT Astra will make your project less efficient and buggy if you let it run loose.
I see people saying they let multiple AI sessions run on their tablet, barely checking generated code and it is very alien to me.
At the current stage, the dev still has to deeply understand the project architecture and give as much context as possible to the AI.
For not so important features (or projects) it is ok to let the AI go wild and fix things later.
It’s all patterns. Down to your thoughts.
that's true actually. we're fickle. it's hard to know what will land and what won't.
yes. i fully expect it to get better at finding problems and deciding what to work on too.
This isn’t my experience. I find that, while the better models make fewer mistakes, a solid percentage of their recommendations and advice are actively harmful to the project. I was fairly “hands off” at the beginning of this project (so much fast progress!) but several months in, I realized what an absolute mess they had made. Every time they added a feature they often duplicated a large portion of the code, other agents did the same and this eventually resulted in an absolute spiderweb of dysfunction. It set me back a few months while i ripped it all out and came up with new processes to force structure, force code reuse and centralization. Just this morning, I caught an agent (grok) in another hallucination. I think that people get good results on smaller blocks of work, but I would worry that if you are fully hands off on a long running project with many cycles, where hallucinations can compound, then you might be surprised as to what they’ve actually written.
https://blossom.primal.net/15563a08e09dd8ea25d3aaa61195c34ef17462f6507b95438c329cfb966403ca.jpg
post-syntax 😂 i like that
