"Coding was never the hard part. Typing syntax into a machine has always been the least interesting part of building a system."
and I think these people are benefitting from it the most, people with expertise, who know their way around and knew what and how to build but did not want to do the grunt work
Slight adjustment, but I'd see "maintaining code" is the same as before, matters more the people and their experience and knowledge how to manage that. But agree that the literal typing was never the difficult part, knowing what code should and shouldn't be written was a hard part, and still remains a hard part.
Right now, "what code shouldn't be written" seems to have become an even more important part, as it's so easy to spit out huge amounts of code, but that's the lazy and easy way, not the one that let you slowly add in features across a decade, rather than getting stuck with a ball of spaghetti after a weekend of "agent go brrr".
this is where years of experience working with freshers and junior devs helps, AI is smart enough to exactly do if you clearly tell it what to do and how
unless you understand every inch of system and foresee what issues can be created by what kind of change, things will break when using AI
Hm. People that know what they are doing prefer to do it themselves. This is not a new thing, not because of llms, but it is how it was always. People that knows more, have heavier opinions. Given the option of accepting new code and new functionality, often, people that knows what they are doing would reject code that functions fine, but fails expectations.
I think who's benefiting the most are people that said that syntax was the least interesting parts but could not program for shit.
Typing into a machine is not the least interesting part. It is the only interesting part. Everything else is a fairy tale
There are people who just want an object produced that allows for some outcome to be achieved closer to the present.
And there are other people who want to ensure that object that is produced, will be maintainable, not break other parts of the system etc.
Neither party is wrong in what they want. I think there should naturally be a split of roles - the former can prototype stuff so other individuals in the organisation can critique whether it is a thing of value / worth investing in for production.
me and my team have wasted so many hours (days) working on some product features which was "definitely going viral" only to be forgotten after a few weeks
I believe if we had something like this we could go to market early and understand the user behaviour to build a more scalable and robust system once we were sure if it was even of worth
I believe it is the way it is because it would cost too much otherwise. You can use the live API for continuously monitoring what the user is doing and if they are stuck but that would be expensive.
You are right. Streaming every keystroke via a Live API would bankrupt me on day one. My current thought is to fake the 'live' feel using client-side heuristics. I'd only ping the LLM on specific events: a 60-second typing idle timeout, or intercepting the payload when they hit 'Run' and fail a test case. Do you think relying on frontend triggers like that is enough to make the UX feel proactive?
"I once believed I could help the people building A.I. get ahead of the problems it would create. This week confirmed my slow realization that OpenAI seems to have stopped asking the questions I’d joined to help answer."
They were given 1.5 YEARS of lead time. And FLOSS should treat commercial entities the same way they treat us.
Seriously, if we copied in violation their code, how many hours would pass before a DMCA violation?
FLOSS should be dictatorial in application of the license. After all, its basically free to use and remix as long as you follow the easy rules. I'm also on the same boat that Android phone creators should also be providing source fully, and should be confiscated on import for failure of copyright violations.
But ive seen FLOSS devs be like "let's be nice". Tit for tat is the best game theory so far. Time to use it.
My understanding is that the GPL doesn't have fucktons of precedent behind it in court. You bet the house on a big case and lose, the precedent will stick with GPL and may even weaken all copyleft licenses.
Also, it's better to gently apply pressure and set a track record of violators taking corrective measures so when you end up in court one day you've got a list of people and corporate entities which do comply because they believed that the terms were clear enough, which would lend weight to your argument.
It definitely does have precedent in multiple jurisdictions. Heck, SFC just won against Vizio enforcing the GPL's terms in the US, and there have been previous wins in France and Germany.
Most licenses, EULAs, contracts and so on don't have much precedent in court. There's no reason to believe that GPL would fold once subjected to sufficiently crafty lawyers.
AFAIK it has enough precedent (also depending a bit on jurisdiction, but you only need one) but the interpretations of what that/the license should cover differ. Like f e if you wanted to argue driver devs would have to open-source their firmware blobs or their proprietary driver loaded by a kernel shim you will have a tough time and prob lose
its such a fascinating thing that most people just ignore
i too wrote (using AI) an article on Branch Prediction after i found out that most of my team members only read this in college but never understood
and I think these people are benefitting from it the most, people with expertise, who know their way around and knew what and how to build but did not want to do the grunt work
reply