334 karma · joined June 17, 2024
The reality of problems such as this one is you don't discover them until the product is in a user's hand for awhile, so while LLMs may be useful is speeding up the resolution of these problems they're kind of useless at discovering them. Yet despite this CEOs of companies with major AI investments are promising an idealized future within a couple of years as though it hasn't already been nearly 3 years of ChatGPT. Despite all the hype and promises the pace of the product development lifecycle seems to remain unchanged. I think realistically it'll be at least 10 years before LLM-based tools and agents can do what CEOs are promising.
Money is how you define a Golden Age of Programming? I consider the late 1990s and early 2000s more of a Golden Age, and my reasons for it have nothing to do with making money. The time was of Golden Age because that's when programming became more accessible to the masses. Yes it wasn't without its fault, namely with regards to cyber security, but people all of the world suddenly were able to learn how to code and all the needed was an Internet connection.
Frankly, all this nonsense about money, total compensation, etc. is the cancer that killed programming.
Instead of just blindly rattling off a bunch of buzzwords that you know nothing about maybe select 1 or 2 of the things from your list you actually have experience in.
1. Every generation of programmers typically only has a certain window of knowledge, and everything before their time is simply foreign to them. Most developers aren't programming history buffs, they don't read books from the past to learn about technologies or how they work, how we got to now, etc.
2. When you're starting off on your journey as a programmer you're using a lot of things without understanding their implementation, and that understanding for most individuals whom I've worked with comes from having to debug issues.
However, if you're expecting it to write an entire OS from a single prompt it's going to fail just as any human would also fail. Complex software problems are solved incrementally through planning. If you do all of that planning its not hard to get LLMs to do just about anything.
Basically, how I've become successful using LLMs is that I solve the problem at a 9,000ft view, instruct the LLM to play different personas, have the personas validate my solution, and then instruct the LLM step-by-step to do all of the monkey work. Which doesn't necessarily always save me time upfront but in the long run it does because it makes fewer mistakes implementing my thought experiment.
I want it to be like a C64-style keyboard with all the guts inside it but wirelessly connect to the display/tv, so what I might do is use an ESP32 to read the game floppy and wirelessly transfer and cache the file to a dongle that plugs into an open HDMI port. Not sure yet.
You could just use SQL but then you'd have to develop and test the entire infrastructure to support your component-oriented architecture from scratch, and at that point you're kind of just reinventing the wheel because that's basically just pandas with less features.
Low-code is kind of just Authorware for a new generation... assuming you're old enough to remember that technology.
Within the past 40 years they used to lock people like me up, give us lobotomies, forcibly medicate us, etc. Its easy to forget how society used to treat folks with mental illness. Its frankly no wonder that people to this day still hide it. Heck, I've had to contact the EEOC more than once. But the thing is, social-media didn't cause this, video games didn't cause this. I've always been genetically predisposed to this. In my opinion, unfettered access to the Internet in general is probably the worst environment for people with predispositions, but to simply blame everything on the environment we've create online through video games or social-media is wrong if not irresponsible.
That's not exactly true per se. My wife is from the country of Tunisia and my plan was to live and work from there, but once I got to the offer stage at each and every company said I must work within the US citing IRS regulations. While I'm not entirely clear why I've also seen a number of remote jobs that are only eligible in certain states within the US as well.