61–70 of 328 posts
Earlier quoted context omitted.
A higher level of abstraction that doesn't require thinking? Did you mean to write thinking here?
Higher levels of abstraction require more complex levels of thinking. Why do you think it won't?
I can't relate that much to this. Every time I use AI to write code, I'm constantly fighting a feeling on the back of my neck that I need to look over everything it has done and supplement/alter it with my own code. That ick feeling counteracts the dopamine hit of having a working app after a few minutes of vibe coding, and I don't think that's going anywhere anytime soon. That said, I have experience. I could absolu…
We'll just move to a higher level of abstraction; thinking will be like efficiently coding in assembly, no longer necessary in today's world.
People say this constantly, but it's a qualitatively different jump from all previous abstraction layers. Previously, the part of your brain you had to use, and the way you had to think, changed from old layer X to new layer Y, but they were still very similar qualitatively. A person who was good at and enjoyed layer X either naturally was good at and enjoyed layer Y, or they could achieve both of those things after…
I unironically believe this is a very good habit. When it comes to writing, instead of starting with AI, finish a chapter by hand first then ask AI to review it strikes the best balance.
Earlier quoted context omitted.
Fastest is usually the wrong metric. But you'd need experience to know that, I suppose...
But the point is that LLMs giving you 10x the potential code output doesn't have to mean 10x the code committed . It can also be "let's look at all three possible implementations in more detail and decide which is really the best fit for our situation, and commit that one." That's still 2-3x the velocity, but you get a better result because you went deeper on the paths-not-taken when designing.
It converts ICs into project managers, by default. I've been wrestling with this issue for a year.
There are things that I think are very cool; there are lots of projects that I've sort of wanted to do for the last decade that I have pushed off because they're reasonably high effort and I don't want them that much, so being able to have a pretend intern write it for me has been great.
On the other hand, I do think that using Claude/Codex to do all the coding at work has become a little soul sucking. Now instead of being paid to do fun software work, a lot of my work still boils down to babysitting interns.
When I do get to work on projects that are interesting, it's still fun because I can justify writing TLA+, and using that as a guiding spec for my projects. The problem is that most work really isn't that interesting; a lot of it is glorified SQL queries, or CRUD, or "put thing into Kafka in one place, and take it out in another place". Those jobs can be tedious, but they aren't interesting, and now instead of even getting that, I yell at Codex to do it and I awkwardly sit and wait.
I didn't think I'd miss writing stupid CRUD apps, but here we are.
It doesn’t have to be this way. You can use AI in ways that don’t rot your brain. You can delegate easy tasks to the AI to save time, while saving the harder tasks for yourself. Or you can treat it more as a mentor / tutor and have it explain why it made certain decisions. I find that AI fails at things that are truly creative. I have been thoroughly unimpressed with ideas it has had or things it’s written for me. Th…
I have a pet theory that perhaps the optimal way to use AI will be more like an "exoskeleton" that turns you into a super-human programmer. Something that plugs the deficiencies of the human programmer, rather than replacing you entirely.
We'll just move to a higher level of abstraction; thinking will be like efficiently coding in assembly, no longer necessary in today's world.
People say this constantly, but it's a qualitatively different jump from all previous abstraction layers. Previously, the part of your brain you had to use, and the way you had to think, changed from old layer X to new layer Y, but they were still very similar qualitatively. A person who was good at and enjoyed layer X either naturally was good at and enjoyed layer Y, or they could achieve both of those things after…
Earlier quoted context omitted.
Higher levels of abstraction require more complex levels of thinking. Why do you think it won't?
The entire point of abstraction layers is that they require less thinking most of the time (and, usually as a tradeoff, more thinking a minority of the time).
Like GC langauges help me do more productive work by hiding useless info about memory