Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI, Tools and Transformation

ben-evans.com

Post reply on HN
Print view View original

61–70 of 85 posts

Re: AI, Tools and Transformation

#61

Post by skydhash »

raincole wrote: post #48
Xirdus wrote: post #40

Earlier quoted context omitted.

Maybe not all AIs, but LLMs benefit immensely from abstraction. They are trained on human code, and human code usually uses very high abstraction - so high abstraction is overrepresented in training data compared to low level implementations. It also drastically reduces number of tokens, and that has downstream effect of better utilization of context window and whatnot. We are not yet at the point where AI can use lo…

I've never encountered a case where I tell AI just uses plain JavaScript instead of React and it doesn't result in much cleaner code.

Have you tried using it in the case where React is actually a good help (very interactive apps)? And try to generate vanilla code for that as well?

Re: AI, Tools and Transformation

#62

Post by lelanthran »

jaynetics wrote: post #10
ryuuseijin wrote: post #2

> You need audit, security, maintenance and accountability. I think this is where the role of humans will move towards in the future. Things like accountability can't really be outsourced to AI. This relates to solving the alignment problem: if you give the AI a specific goal and it has to plan sub-goals, how can you be sure the sub-goals align with your interests. For tasks in an isloated environment, this doesn't r…

I think most developers and most dev work is now in the field of websites, apps, and other stuff that is by nature connected to the internet, and has some relatively monolithic backend that has not been built with "blast doors" or other internal safeguards. I guess it will take considerable time until most software is in a state where the impact of AI changes can be reliably estimated without looking at the changes t…

> I expect the gruesome writing style of LLMs to be fixed relatively soon, seeing how it can already be prevented with just a few lines of stylistic instructions.

I have not found this to be the case even with SOTA models as recently as last month.

It holds for a short while into the content but reverts very quickly to its default style.

The default style is so heavily embedded in the weights I don't think simply adding prompts will help.

Re: AI, Tools and Transformation

#63

Post by ordersofmag »

raincole wrote: post #48
Xirdus wrote: post #40

Earlier quoted context omitted.

Maybe not all AIs, but LLMs benefit immensely from abstraction. They are trained on human code, and human code usually uses very high abstraction - so high abstraction is overrepresented in training data compared to low level implementations. It also drastically reduces number of tokens, and that has downstream effect of better utilization of context window and whatnot. We are not yet at the point where AI can use lo…

I've never encountered a case where I tell AI just uses plain JavaScript instead of React and it doesn't result in much cleaner code.

If what you're trying to build is a perfect match for the full set of abstractions React provides then it's gonna be cleaner to use React than have AI re-invent it. But most cases I run into don't fit that description.

Re: AI, Tools and Transformation

#65

Post by loh »

zacksiri wrote: post #4

The way I see it is AI collapses hierarchy. Abstraction layers will become more flat both in software and in society. Because ultimately software and layers of heirarchy in society exists to serve a function. But now those functions are being replaced. Imagine this you used to need a library for common things in your software project. Even if you just need one function but because it was easier to just import a libra…

There is still a lot of work do be done surrounding the systems AI integrates for us, and as a sibling comment mentioned, AI's ability to use various abstractions is incredibly beneficial, as it results in fewer tokens (not reinventing the wheel) and can provide more consistent/predictable polished results. If you're building something trivial like a basic web page or a very simple one-off script, sure, abstractions would be overkill. But if you're building something that needs to scale and interface with many other systems and work perfectly on every available platform, we still need abstractions that AI can work with.

I don't think we've seen the end of the library/framework churn from the last few decades before AI, but I do think we will eventually settle on an "optimal approach" where the average developer no longer has to consider tool A versus tool B for basically every common use case. Future libraries and frameworks will be designed specifically for AI to "understand". Most LLM training data is based on the old way of building software, and while it is pretty good at it, I think we'll see major improvements (and counterintuitively, less AI slop) as the underlying abstractions and AI models adapt to the new paradigms and workflows enabled by AI.

Re: AI, Tools and Transformation

#66

Post by getlawgdon »

ryuuseijin wrote: post #2

> You need audit, security, maintenance and accountability. I think this is where the role of humans will move towards in the future. Things like accountability can't really be outsourced to AI. This relates to solving the alignment problem: if you give the AI a specific goal and it has to plan sub-goals, how can you be sure the sub-goals align with your interests. For tasks in an isloated environment, this doesn't r…

I agree. I think accountability is the future.

Re: AI, Tools and Transformation

#67

Post by jaynetics »

beecasthurlbow wrote: post #52
jaynetics wrote: post #10

Earlier quoted context omitted.

I think most developers and most dev work is now in the field of websites, apps, and other stuff that is by nature connected to the internet, and has some relatively monolithic backend that has not been built with "blast doors" or other internal safeguards. I guess it will take considerable time until most software is in a state where the impact of AI changes can be reliably estimated without looking at the changes t…

> I expect the gruesome writing style of LLMs to be fixed relatively soon, seeing how it can already be prevented with just a few lines of stylistic instructions What instructions do you use to prevent the gruesome writing style? I have… not found this to be the case.

Currently I append the snippet below to prompts where I care about the resulting text. Just putting it in the context up front isn't as effective, and I assume if the overall prompt is large, or the context window is full, it will also be less effective.

> Use plain, clear, everyday language with a linear deductive flow; avoid hyperbole, juxtapositions, metaphors, analogies, punchlines.

Re: AI, Tools and Transformation

#68

Post by novok »

yoz-y wrote: post #13
zacksiri wrote: post #4

The way I see it is AI collapses hierarchy. Abstraction layers will become more flat both in software and in society. Because ultimately software and layers of heirarchy in society exists to serve a function. But now those functions are being replaced. Imagine this you used to need a library for common things in your software project. Even if you just need one function but because it was easier to just import a libra…

I am honestly _astonished_ that the current crop of agents are not all written natively for every platform. I tried porting a moderately complex workout app that I’ve built over years (and which includes a whole agentic loop) from web to iOS native. It took me a couple of evenings. There is now no excuse to not offer a native experience for every supported platform when you are a bigger company. Make one of the platf…

If you actually try to implement the same app in multiple platforms from the same spec, you'll notice very quickly that AI makes the best quality UIs out of typescript electron or direct web. It accomplishes it's task the fastest, with the least lines of code and with the least bugs. Also hot patching updates works best with web.

And I say this as a person who isn't a web dev, but a mobile dev. This is why.

AIs are also really good at translating one complete app from one language to another where nothing changes. You'll also notice that new features will be implemented better in typescript web than iOS going further. I think this is why OpenAI changed their native swift chatgpt desktop app into web electron too.

Re: AI, Tools and Transformation

#69

Post by jaynetics »

lelanthran wrote: post #62
jaynetics wrote: post #10

Earlier quoted context omitted.

I think most developers and most dev work is now in the field of websites, apps, and other stuff that is by nature connected to the internet, and has some relatively monolithic backend that has not been built with "blast doors" or other internal safeguards. I guess it will take considerable time until most software is in a state where the impact of AI changes can be reliably estimated without looking at the changes t…

> I expect the gruesome writing style of LLMs to be fixed relatively soon, seeing how it can already be prevented with just a few lines of stylistic instructions. I have not found this to be the case even with SOTA models as recently as last month. It holds for a short while into the content but reverts very quickly to its default style. The default style is so heavily embedded in the weights I don't think simply add…

> It holds for a short while into the content but reverts very quickly to its default style.

You can always make it do a second pass, and if that isn't enough, even let it fix each generated text block individually.

Re: AI, Tools and Transformation

#70

Post by lasky »

AI will make the asset holders more productive and profitable.

It will raise the level of personal agency + stable family resources required to avoid crises and homelessness.

Society will increasingly organize around preventing class warfare.

Post reply on HN