I don't think Daniel's point is that Chat is generically a clunky UI and therefore Cursor cannot possibly exist. I think he's saying that to fully specify what a given computer program should do, you have to provide all kinds of details, and human language is too compressed and too sloppy to always include those details. For example, you might say "make a logon screen" but there are an infinite number of ways this could be done and until you answer a lot of questions you may not get what you want.
If you asked me two or three years ago I would have strongly agreed with this theory. I used to point out that every line of code was a decision made by a programmer and that programming languages were just better ways to convey all those decisions than human language because they eliminated ambiguity and were much terser.
I changed my mind when I saw how LLMs work. They tend to fill in the ambiguity with good defaults that are somewhere between "how everybody does it" and "how a reasonably bright junior programmer would do it".
So you say "give me a log on screen" and you get something pretty normal with Username and Password and a decent UI and some decent color choices and it works fine.
If you wanted to provide more details, you could tell it to use the background color #f9f9f9, but a part of what surprised my and caused me to change my mind on this matter was that you could also leave that out and you wouldn't get an error; you wouldn't get white text on white background; you would get a decent color that might be #f9f9f9 or might be #a1a1a1 but you saved a lot of time by not thinking about that level of detail and you got a good result.
I don't know why everybody thinks Microsoft Word doesn't have Reveal Codes. They have it; it's called Reveal Formatting; it has mostly been there since version 1.0 which I remember installing from 100 floppy disks in college in 1989.
Google sort of has a preprocessor that does stuff like this. Probably not as much as Wolfram.
You can see it when you search Google for things like:
"What time is it in Las Vegas" (notice that it knows, and it also knows that you probably mean Las Vegas NV but might mean NM, and that Las Vegas NM is smaller)
"MSFT" (e.g. a ticker)
"Who is the president of France"
"16 USD in GBP"
From the stories, it SOUNDS like Wolfram can answer a lot more of these kinds of queries than Google, which makes me think that the best way to use a technology like this is to sell it to Google to plug in as their pre-search pre-processor to replace the simple ones they've already developed.
If you asked me two or three years ago I would have strongly agreed with this theory. I used to point out that every line of code was a decision made by a programmer and that programming languages were just better ways to convey all those decisions than human language because they eliminated ambiguity and were much terser.
I changed my mind when I saw how LLMs work. They tend to fill in the ambiguity with good defaults that are somewhere between "how everybody does it" and "how a reasonably bright junior programmer would do it".
So you say "give me a log on screen" and you get something pretty normal with Username and Password and a decent UI and some decent color choices and it works fine.
If you wanted to provide more details, you could tell it to use the background color #f9f9f9, but a part of what surprised my and caused me to change my mind on this matter was that you could also leave that out and you wouldn't get an error; you wouldn't get white text on white background; you would get a decent color that might be #f9f9f9 or might be #a1a1a1 but you saved a lot of time by not thinking about that level of detail and you got a good result.