You can use them for dev environments.

You just have to finish development in 8 hours.

It would not, and you would know that if you actually evaluated the results.

I have gone through this process and evaluated the results. Maybe you're referring to their comment as written, but going through what OC described + handholding leads to very good results in my experience.

I agree with you agentdev! Here, you want accurate results, you need to have harness in place to control the quality of output.

"very good" 99 percent of time and hallucinating 1 percent makes the "very good" part untrustworthy.

It's not weird, since 99% of rentals are apartments, right?

Source? In my neighborhood on the outskirts of downtown (about a 10 minute drive out) at least 25% of the houses are rentals, maybe more like 33%. Lots of investment properties people scooped up when mortgages were 2%.

I agree in principle, but I think the 2-5% estimate is extremely low. I could be sold on most developers spending ~25%, up to 40% of their time on code. But very few people are spending 2% of their time on it. Unless you're some sort of super senior staff / advisor to the CTO at a gigantic company, which has already placed you on rare terrain.

Most people overestimate how much time they spend "writing code".

I interviewed a ton of people in my career and when I ask "how much time writing code on your last job?". The more junior the person the more they would overestimate the time writing code (Some would say 90%!). Once they joined I was able to see how much time they really wrote code and it is almost never more than 30%.

Mostly because the code is only the final output. You spend most of your time doing research, talking to people. Working on Quarterly OKRs, going to meetings etc.

If you just write code you are either an extremely junior person that works on things trivial enough to not have to research or your are disillusioned and you don't realize you spend most of your time doing other things

might be closer to accurate if the 2-5% is his estimate of the physical time spent making key-strokes

Surely we should only count the time actuating the key. Apple keyboard users are in shambles.

Only the keydown, not the keyup.

That's <24 minutes per 8 hour day.

If you're reading this and that matches your experience as an IC SWE whose job is ostensibly developing software.. you're either trapped in a very atypical org, or you're heading for a PIP.

Nope. I would bet most people really only do 2-10%.

But we would like to convince ourselves we don't.

This is a really, really, really bad comparison. I used to say the same thing. But the semantic distance between compiling a for loop to equivalent assembly instructions is much smaller than the distance between "I'd like a web application that can store and retrieve todo items." The space of the latter is practically infinite in what can be "compiled."

A counterpoint, since I never made that logical jump in your latter part of your comment: programming languages are, functionally, all domain-specific languages and do a good job of either describing directly, or consistently, deterministically, providing a reasonable and unambiguous abstraction over low-level concepts expressed by assembly languages.

Human languages are mostly very bad at this, and in particular bad at mapping low-level abstraction to the human written word unambiguously in a way that is as expressive as programming languages.

Inference closes that specific gap significantly (which is why anyone at all sees LLMs as a useful option to explore), but it will never be as good as a purpose-built language designed to map to a reasonable corresponding assembly language implementation.

Yes you're missing something: the snake oil.

I think so, yea.

Give it a shot

It 100% implies that it's looking for locally installed binaries.

And could possibly access private documents if it wanted to, etc.

So is human coding.