> However, a leaked system prompt for Claude’s artifacts feature shows that both React and Tailwind are specifically mentioned.
Damn.
AI is stifling new tech adoption?
241–250 of 442 posts
Re: AI is stifling new tech adoption?
#242…Isn’t this the website that constantly encourages people to “choose boring technology” for their web tech startups?
Aren’t a reasonable portion of the readers here people who bemoan the constant learning curve hellscape of frontend development?
And now we’re going to be upset that tools that help us work faster, which are trained on data freely available on the internet and thus affected by the volume of training material, decide to (gasp) choose solutions with a greater body of examples?
Just can’t satisfy all the people all the time, I guess! SMH.
Re: AI is stifling new tech adoption?
#243Earlier quoted context omitted.
> And I also found the basic tier of ChatGPT hallucinated my app's purpose in a way that was borderline slanderous. I'm curious about this, what exactly did ChatGPT write and how was it borderline slanderous? Sounds like a big danger.
So ChatGPT seemingly guessed its purpose just from its name. Its name is CurrentKey Stats, and it inaccurately described it as an app that kept stats on the current keyboard keys you were pressing, so essentially a key logger, which is again completely wrong. I was actually somewhat hesitant to make this comment out of the fear that the next AI models will train on it and reinforce the false idea that that's what my…
You may be happy to learn that I just asked ChatGPT (the free tier that you can access without signing in) "What does the CurrentKey Stats app do?" and got this back:
----
CurrentKey Stats is a macOS application designed to enhance your productivity by offering detailed insights into your app usage and providing advanced management of your Mac's virtual desktops, known as "Spaces."
Key Features:
Time Tracking: Unlike macOS's Screen Time, which tracks total app usage, CurrentKey Stats monitors the time each app spends in the foreground, offering a more accurate representation of active usage.
Room Management: The app allows you to assign custom names and unique menu bar icons to each Space, facilitating easy identification and navigation. You can switch between these "Rooms" using the menu bar icon or customizable hotkeys.
Automation Support: For advanced users, CurrentKey Stats supports AppleScript, enabling you to automate actions when entering or leaving specific Rooms. This feature can trigger scripts to perform tasks like launching applications, adjusting system settings, or controlling smart home devices.
Privacy-Focused: The application prioritizes user privacy by keeping all data local on your device, ensuring that your usage statistics are not shared externally.
By combining detailed app usage statistics with enhanced Space management and automation capabilities, CurrentKey Stats aims to help you use your Mac more efficiently and deliberately.
----
But more generally, I think people often look at LLMs and assume that the current flaws will be around forever and this will be horrible. But all technologies have big, obvious flaws when they're first introduced and these get fixed because there's a strong incentive to have a less bad product.
Re: AI is stifling new tech adoption?
#244Earlier quoted context omitted.
I'll accept an analogy with a hybrid car. In this analogy, Preact would be a gas car with an additional electric engine bolted on as an afterthought.
But you know, the Prius Prime is a PHEV as in "plug in hybrid electric vehicle"
Oh, I see what you mean now! This sounds like a very good analogy.
Re: AI is stifling new tech adoption?
#245One thing that is interesting is that this was anticipated by the OpenAI Codex paper (which led to GitHub Copilot) all the way back in 2021: > Users might be more inclined to accept the Codex answer under the assumption that the package it suggests is the one with which Codex will be more helpful. As a result, certain players might become more entrenched in the package market and Codex might not be aware of new packa…
ChatGPT and Gemini default to create-react-app, which has been considered poor practice for 2 years at least.
Re: AI is stifling new tech adoption?
#246Re: AI is stifling new tech adoption?
#247Earlier quoted context omitted.
[flagged]
This website is mostly full of very junior developers that just click on articles they think "sound smart" or are a hot take they agree with. Don't get me wrong, it's also one of the few places where you find experts from all sorts of industry mingling. But the quality of commentary on HN has plummeted in the last 10 years.
"Please don't sneer, including at the rest of the community." It's reliably a marker of bad comments and worse threads.
Re: AI is stifling new tech adoption?
#248>Consider a developer working with a cutting-edge JavaScript framework released just months ago. When they turn to AI coding assistants for help, they find these tools unable to provide meaningful guidance because their training data predates the framework’s release. [... This] incentivises them to use something [older]. That sounds great to me, actually. A world where e.g. Django and React are considered as obvious…
> A world where e.g. Django and React are considered as obvious choices for backend and frontend as git is for version control sounds like a world where high quality web apps become much cheaper to build.
Imagine you saying this twenty years ago. Would you still want to be writing your back-end in JavaBeans, your front end in VisualBASIC, and storing your data in Subversion?
Re: AI is stifling new tech adoption?
#249I actually asked this a while back, but got little response: https://news.ycombinator.com/item?id=40263033 > Ask HN: Will LLMs hurt adoption of new frameworks and technology? > If I ask some LLM/GPT a react question I get good responses. If I ask it about a framework released after the training data was obtained, it will either not know or hallucinate. Or if it's a lesser known framework the quality will be worse tha…
I like what FastHTML folks did by preparing what amounts to instructions for LMs. From their Github [1]: > This example is in a format based on recommendations from Anthropic for use with Claude Projects. This works so well that we’ve actually found that Claude can provide even better information than our own documentation! This is the file: https://docs.fastht.ml/llms-ctx.txt [1] https://github.com/AnswerDotAI/fasth…
I do not know how FastHTML works with AI, but for the recent Svelte 5, which has a similar llms.txt file, it's clear to me that actual usage patterns are required over explanatory llms.txt content with instructions. In Svelte 5 usage, it's consistent at certain things which the docs spell out for version 5 and would not be in the training data (runes) but not in their placement, reactivity, or usage changes implied by the system (e.g. changes of information flow outside of props/states)
It seems similar to a cheat sheet which has formulas, vs a cheat sheet with worked through sample problems that align perfectly with the test.
The latter exists for historic modules - the former is the best you can do for recent libraries/versions.
I am not sure where React stands as I know they have changed their reactivity model and introduced patterns which reduce boilerplate code. Can anyone comment on the latest react version used with AI?
Re: AI is stifling new tech adoption?
#250One thing that is interesting is that this was anticipated by the OpenAI Codex paper (which led to GitHub Copilot) all the way back in 2021: > Users might be more inclined to accept the Codex answer under the assumption that the package it suggests is the one with which Codex will be more helpful. As a result, certain players might become more entrenched in the package market and Codex might not be aware of new packa…
ChatGPT and Gemini default to create-react-app, which has been considered poor practice for 2 years at least.
What's considered better practice? NextJS?!