I have been using LLMs (chapt-gpt, perplexity, claude) for development for over a year. It is helpful for summary explanations of concepts and boilerplate for frameworks and library APIs. But it makes errors within those consistently.
Its a great tool and saves a great deal of time, but I have yet to go beyond generating snippets I have to vet, typically finding a made up library API call or misunderstanding of my natural language prompt.
I find it hard to pare down these LLM evangelizing articles into take aways that improve my day to day.
I know it is in the nature of probabilistic neural network outputs, but it almost feels like these commercial models are built to make those mistakes (making up functions/parameters) and it is all a big conspiracy to hide the real useful stuff from general public.
I started giving the models api docs and headers before interacting with them and it seems to work a lot better.
I think it was their exceptional design in the 2000s. They were never the first, but they were exceptional at appearing to be an innovator on the originality of their product design. I have not been impressed with apple design innovation for some time though, they've gotten stale.
Much of the innovation, for better or worse, happens in miniaturization, power & thermal management, and supply chain. Apple's inventory turns are insane.
The walled garden certainly keeps me out of the apple ecosystem. I love MacOS but I don't want to pay a premium for vendor lock-in and I infer that most (if not all) apple products are double-edged in that manner.
I personally think this is the major reason their ratings are so low. My parents want to watch Ted Lasso, and I told them to subscribe and watch it. "We can't, we have a roku, and I'm not paying $200 for another box." Imagine millions doing this and you see the result.
To be fair the device and service have, like, the same name. Assuming some relationship between them is obvious. Also, this is Apple, the guys who are very dedicated to pairing hardware and software together.
That's funny because I know a lot of people on the other side of the fence that leave teaching for even lower paid work because it is miserable and unfulfilling.
Given this knowledge, it's hard to you comments like this any differently than comments from googlers talking about how fulfilling it would be to work a construction job or romanticize pre-industrial Society from a downtown penthouse
Why not become a private teacher, aka trainer / instructor. 3x may not be even close to the top of the potential upside (if using modern elearning tech, and having good subject knowledge and some decent marketing).
Ah yes, just what teachers love doing, being monetarily beholden to the parents of the little brat causing all the problems because they pay $50k a year
That's partly because due to the fulfilling nature of the work (a compensating differential), and partly because we can't price it (how much is it worth?)
Some of them are great but then I remember when I was floating around research labs some grad students would cry and tell you not to do what they were doing because its miserable. But then life has many fun horrors does it not?
Agile is an adjective, not a noun. The opposite of agile are words like clumsy, apathetic, depressed, dispirited, down, dull, ignorant, inactive, lazy, lethargic, lifeless, rigid, slow, sluggish, stiff, stupid, brittle, etc. That's why being agile caught on because none of the opposites sound like a good thing to admit to.
That's why agile is a bit vague and waffly as well. Because world+dog now calls themselves agile. And then you get all these pedantic types telling others they are doing it wrong, aren't pure enough, etc. They are the priests of agile. And they get hired by big companies for lots of money to help them become agile. Of course that requires some compromise and they adapt their definitions and standards until it's all agile and wonderful. Because the alternative would be admitting failure, which isn't mutually beneficial. You are kind of doing waterfall in an agile way For example, you plan 20 scrum sprints ahead and then act surprised reality has different plans. It's still as dumb as waterfall ever was.
Most of these companies of course deliver software just fine. They don't do it particularly fast. Or well. Also they aren't that flexible. Or particularly quick to adapt to changing circumstances. I.e. all of the things one would associate with being agile (in the adjective sense). But it's good enough to call themselves agile and still feel good about it.
People were doing awesome software long before agile development became a thing. That was never conditional on being agile (whatever that means). I've been around long enough to have seen the before and after the post-it shufflers came in and made our walls all colorful. And I can tell you that the average software project is just about the same level of a disgraceful mess as it was thirty years ago. We do a bit more of it and a bit differently. And we got some nice tools that remove some bottlenecks from our process (like automated tests and CI) and make us more productive That's not agile, it's using better tools and it helps. The tools definitely improved massively in thirty years.
"And can you update the detailed plan now that we've decided to change a fundamental decision that invalidates half your planning? That'd be great mkay."
