61–70 of 432 posts
Natural language isn’t made to be precise that’s why we use a subset in programming languages. So you either need lots of extra text to remove the ambiguity of natural language if you use AI or you need a special precise subset to communicate with AI and that’s just programming with extra steps.
We're going to create SQL all over again, aren't we?
I'm growing to the idea that chat is a bad UI pattern, period. It is a great record of correspondence, I think. But it is a terrible UI for doing anything. In large, I assert this is because the best way to do something is to do that thing. There can be correspondence around the thing, but the artifacts that you are building are separate things. You could probably take this further and say that narrative is a terribl…
Incidentally I think that's also a good model for how much to trust the output - you might have a colleague who knows enough about X to think they can answer your question, but they're not necessarily right, you don't blindly trust it. You take it as a pointer, or try the suggestion (but not surprised if it turns out it doesn't work), etc.
I'm growing to the idea that chat is a bad UI pattern, period. It is a great record of correspondence, I think. But it is a terrible UI for doing anything. In large, I assert this is because the best way to do something is to do that thing. There can be correspondence around the thing, but the artifacts that you are building are separate things. You could probably take this further and say that narrative is a terribl…
Midjourney is an interesting case study in this I think, building their product UI as a discord bot. It was interesting to be sure, but I always felt like I was fighting the "interface" to get things done. It certainly wasn't all bad, and I think if I used it more it might even be great, but as someone who doesn't use Discord other than that and only rarely generated images, I had to read the docs every time I wanted…
As is often the case in these sorts of thingsz your milage may vary for the more complex settings.
For me: Chat is like writing comments, but not a the right place in the source code. Perhaps I should comment all todos and then write "finish todos" as the always-same text prompt.
And that's not even to say that I don't write code comments. When working on large legacy codebases, where you often need to do 'weird' things in service of business goals and timelines, a comment that explains WHY something was done the way it was is valuable. And I leave those comments all the time. But they're still a code smell.
Comments are part of your code. So they need to be maintained with the rest of your code. Yet they are also "psychologically invisible" most of the time to most programmers. Our IDEs even tend to grey them out by default for us, so that they get out of the way so we can focus on the actual implementation code.
This means that comments are a maintenance obligation that often get ignored and so they get out of sync with the actual code really fast.
They also clutter the code unnecessarily. Code, at its best, should be self-explanatory with extremely little effort needed to understand the intent of the code. So even a comment that explains why the code is weird is doing little more than shining a flashlight on smelly code without actually cleaning it up.
And don't get me started on "todo" comments. Most professional shops use some kind of project management tool for organizing and prioritizing future work. Don't make your personal project management the problem of other people that share and contribute to your codebase. There is zero rationale for turning shared code into your personal todo list. (and it should be obvious that I'm talking about checked in code .. if it's your working branch then you do you :) )
So if programming using LLMs is similar to writing comments (an interesting analogy I hadn't considered before), then maybe this is part of the reason I haven't found a problem that LLMs solve for me yet (when programming specifically). I just don't think like that when I'm writing code.
Earlier quoted context omitted.
It does have to be careful at times if you’re going to be effective with natural language.
Certainly there is a need for care outside of computers too, like in law, but legal documents are a prime example of programs. That's programming, written using a programming language, not natural language. It is decidedly not the same language you would use for casual conversation and generally requires technical expertise to understand.
An LLM can do increasingly well as a fly on the wall, but it’s common for people using an LLM to be less collaborative with an LLM and for them to expect the LLM to structure the conversation. Hence the suggestion to be careful in your prompting.
I'm growing to the idea that chat is a bad UI pattern, period. It is a great record of correspondence, I think. But it is a terrible UI for doing anything. In large, I assert this is because the best way to do something is to do that thing. There can be correspondence around the thing, but the artifacts that you are building are separate things. You could probably take this further and say that narrative is a terribl…
As a written form of "stream of consciousness", it seems to have a lot of value to me. It's noisy, inefficient & meandering -- all the things those polished artifacts are not -- but it's also where you can explore new avenues without worrying about succinctness or completeness. It's like the first draft of a manuscript.
Even with game development. Level editors have a good history for being how people actually make games. Some quite good ones, I should add.
For website development, many template based systems worked quite well. People seem hellbent on never acknowledging that form builders of the late 90s did, in fact, work.
Is it a bit nicer that you can do everything through a dialog? I'm sure it is a great for people that think that way.
The example shows "Sign-in screen" with 4 (possibly more) instructions. This could equivalently have been entered one at a time into 'chat'. If the response for each was graphic and instantaneous, chat would be no worse than non-chat.
What makes non-chat better is that the user puts more thought into what they write. I do agree for producing code Claude with up-front instructions beats ChatGPT handily.
If OTOH AI's actually got as good or better than humans, chat would be fine. It would be like a discussion in Slack or PR review comments.
I think everyone is aware that chat is not the ideal UI pattern for this. It's just the way current AI models work and generate content - that's why they have this "typewriter" mode, which naturally leads to a chat interface. It's not really a conscious choice, but rather a side effect. And we already see the trend is away from that, with tools like chatGPT Canvas, editors like Windsurf, etc.
Once the models become fast enough to feel instantaneous, we'll probably begin to see more seamless interfaces. Who wants a pair programmer who goes "umm... ahh..." every time you type something? A proper coding assistant should integrate with your muscle memory just like autocomplete. Tab, tab, tab and it's done.
I'm growing to the idea that chat is a bad UI pattern, period. It is a great record of correspondence, I think. But it is a terrible UI for doing anything. In large, I assert this is because the best way to do something is to do that thing. There can be correspondence around the thing, but the artifacts that you are building are separate things. You could probably take this further and say that narrative is a terribl…
I don't know, I'm in Slack all day with colleagues, I quite like having the additional ChatGPT colleague (even better I can be quite rude/terse in my messages with 'them'). Incidentally I think that's also a good model for how much to trust the output - you might have a colleague who knows enough about X to think they can answer your question, but they're not necessarily right, you don't blindly trust it. You take it…