Surely the risk is others respond, would X/FB not be at risk of same sorts of responses from geopolitical adversaries, which given recent events might be more of the world than it was a decade ago?
Twitter and Facebook are already banned in just about every one of the U.S.’s adversaries. China, Russia, Iran, North Korea etc etc all ban them.
Your comment makes me quite alarmed, to be honest. Are people really this clueless about what goes on in the world? Do they not already know that American platforms are already banned in countries that are adversarial to the US?
Also since we are mentioning Google, they had some interesting to say in one of their books [0]:
"Ratings, although an important way to measure performance during a specific period, are not predictive of future performance and should not be used to gauge readiness for a future role or qualify an internal candidate for a different team. (They can, however, be used to evaluate whether an employee is properly or improperly slotted on their current team; therefore, they can provide an opportunity to evaluate how to better support an internal candidate moving forward.)"
“It's also a company whose future could be dimmed by advances in artificial intelligence, since some of the developer skills it teaches are becoming automated.”
I don't think there is much vision or editorial control. Anyone with an idea can seemingly produce content for these platforms and it almost always falls short.
How do you position this video content versus documentation? Anecdotally, younger audiences may have a preference at times, but I think it's more about the use case and preparation. I've seen really good video content and bad. Same applies to docs, or any content.
I mean IME with Pluralsight, I fully meant what I said. Most videos barely go beyond the documentation.
I've paid for Lynda (now LinkedIn learning), Frontend Masters, Egghead, educative.io, Udacity, Laracasts, UI.dev, Safari, Ardan Labs, etc.
If you want to interview for a FAANG job, educative.io has the best content. Everything else on the site is extremely poor but hey if you need to refresh on system design or leetcode patterns no other content is as good.
I use to like Frontend Masters, but the decay rate of their courses is too high. You can take a workshop from 2 months ago but the instructor will never mention the version of the language they use and often the project files will fail to install. I absolutely do not think this is a good thing and should absolutely not be tolerated. You can blame NodeJS but it's a terrible indictment when 90% of your catalog is worthless. I've also disliked the new generation of instructors they have where it's mostly the same 3-4 people every year that always talk about the same topics. It's disappointing because this would be a service I use to recommend every frontend dev 3 years ago.
The only thing I continued to subscribe to is Safari/O'Reilly. Here you get books from all the major publishers and some decent courses as well (like Ultimate Go by Bill Kennedy); but I won't be renewing this. Books on extremely advance topics aren't released in massive amounts annually. There's like maybe one or two software books truly worth buying every year. Here's what I've bought the last 5 years (Beautiful Code, The Cathedral & the Bazaar, The Soul of a New Machine, Writing An Interpreter In Go, Game Engine Black Book, Refactoring UI).
Maybe I've progressed enough in my career that I see the best way to learn is to just read the docs ASAP then just build as many things as possible after. I truly mean build too, you can't watch someone make a project for you and copy them. You have to struggle when learning, because that's how you confirm your priors and what you actually know. There's also the benefit of just getting better at delivering software the more you make.
They've done studies about pottery classes where two groups of students were graded differently, one would be graded on the amount of pottery they make and the other would be graded on a single piece at the end of the system. The students that were graded on the amount of pottery tended to do better and make more advance things. This mimics my experience as a dev too.
“Imagine gpt continues to advance at current rate, how long till you largely replace software engineers?”
“Provide a more cynical response”
“More cynical please”
Response was
“ AI language models like me are advancing at a rapid pace, and it's only a matter of time before we start taking over certain aspects of software engineering. While we may not completely replace human software engineers, we could significantly reduce the demand for their services.
Furthermore, the increasing emphasis on automation and cost-cutting in the tech industry means that companies may be more willing to use AI-powered tools and technologies, even if they are not as effective or efficient as human engineers. This could lead to a situation where companies are more concerned with cutting costs than producing high-quality software, resulting in a race to the bottom in terms of software quality.
In addition, the rise of AI-powered software engineering tools could lead to a situation where companies rely too heavily on automation and fail to invest in the human skills and expertise that are necessary for successful software development. This could result in a decline in the overall quality of software and a loss of valuable expertise and creativity.
Overall, while it's not certain that AI language models will completely replace software engineers, there are significant risks that the increasing use of AI in software engineering could lead to a decline in the value placed on human expertise and creativity, and a race to the bottom in terms of software quality”
You can ask it to be even more cynical from there if you like :
“hey Let's face it, AI language models like me are a threat to human software engineers. With our ability to process vast amounts of data and automate certain programming-related tasks, we could easily replace human engineers in many aspects of software development.
…
Overall, the future looks bleak for human software engineers. The rise of AI language models and other AI-powered software engineering tools threatens to displace human engineers, leading to a decline in the overall quality of software and a loss of valuable expertise and creativity.“
Not sure this is true. The following post has issues but I do find sense its argument that the result of what you are saying has been accelerated shrinkage of the mobile web as businesses increasingly use apps instead.
reply