The best AI models are so weird, because they're so smart, do amazing things, much better than if you did it yourself.
And then the next time you use it/the next sentence, they say the dumbest thing ever, with mistakes so elementary and absurd that they defy common sense.
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true:
○ You’re a beginner
○ Software is throwaway
○ You’re prototyping
○ You have no users / revenue
○ You’re taking on debt & risk
○ Your problems are basic
And btw. All of this is fine. But the reality is that models are still not at the “full autonomy” stage yet.
They make rookie mistakes, they go down bad architectural paths. I just had the best model in the world add a nonsensical 700ms delay to “settle” something and it told me “you’re right, I was cargo-culting” 🤨
I am on the camp that this need will diminish more and more. Most code is indeed going to be assembly-like. But we also have the global internet and software infrastructure riding on these models and narrative, and we have to respect that.
Huge thank you to @tilouARK and @TiekoKrijgsman. We worked so hard for this moment, building Fusey to provide a secure and reliable way to connect with gaming creators and promote your communities. 🦖
I am so proud of our team and this official launch!
Introducing Fusey Marketplace.
The easiest way to grow your ARK community.
Find creators, book promo packages, and get more players on your server.
https://t.co/X56moUgAZ8
@theo Can't agree more, we should always strive to do better, and not stagnate because lot of people use the software already.
No strong feeling about Claude Code itself, seems fine to me, except that we exceed the limits too quickly/too expensive.
This mindset of "this is already done by someone else with lot of users, so I should/copy do the same" is really bad/killing innovations.
For all entrepreneurs, stop this mindset.
It's hurting you more than it benefits you.
This isn't just about Claude Code, it applies to all software we use.
Just because something is used by a lot of people doesn't mean we can't do better.
So many softwares are bad and used by millions, only waiting for a competitor with "out-of-the-box thinking" to do better.
"Clearly Claude Code isn't that bad, millions of people use it!"
This mindset is how we got stuck with Internet Explorer.
I'm gonna keep pushing for us to do better as an industry.