I agree in general, but how are you ever upgrading any of that? Could be a "sleeper compromise" that only activates sometime in the future. Open problem.
A sleeper compromise that cannot execute can still not reach its goal. Generally speaking outdated dependencies without known compromise in a sandbox are still better than the latest deps with or without sandbox.
Sure because it worked great when we tried last time, right? Just spec it out first, and AI will churn out the perfect app. Not.
For anyone who hasn't worked in a waterfall project and would like to try: You are kidding yourself.
There is no such thing as a perfect spec. Read that again and say it outloud.
It took humanity 50 years to figure out that perfect specs are impossible, unless of course you know exactly(!) what you need. And even then, the specs are never complete.
The reality is that we often don't know, and can't know, what we want, exactly, until we actually see and experience what we said we wanted. Then we adjust. Try again.
That's the reality for individuals already. By simply using logic we can deduct that entities made of more than one individual, aka companies, will not behave better. They just make it look better by giving you a nice document that says "we want this!", only to then come around when they see what they got, and to claim "wait, we didn't mean it like so!".
That's just human nature. Not much we can do. AI will not change that.
So when some people think AI will deliver perfect software given perfect specs, hence we have to write the specs first! That is just missing the boat my a mile.
Agile is not a process but a human-friendly way of doing things. It simply says hey you want this? Let me build that and show you. Then let's adjust or move to the next thing. Rinse and repeat. Agile works because it matches how humans think and act. Step by step, day by day.
It’s why I said not those exact things. But already today when developing with agents you get best results from selecting it as much as possible so it can then logically break it into smaller contexts and iterate.
It’s not just dropping in case and getting a functional product. But more up front design seems to work best. Very explicit design.
Simon just explores stuff and writes about them. Doesn't mean he uses LLMs for everyting.Antirez likes to question stuff and make them better. Doesn't mean he uses LLMs for everything.
Also their experience is not my experience. I will make my own choices.
HAHAHAH don't even get me started on how bad anaconda is.
On how slow the installer + interpreter, how they avoided being a part of the usual pip workflow, bloated environment, cross platform inconsistencies, extremely slow dependency resolution, etc etc etc...
Posit has solved similar problems with their Package Manager as well, the benefit being that it's hosted on-prem, but the user has to build wheels for their desired architecture (if they're not on pypi).
reply