I'm happy to hear that! A lot of people posting their hot takes here about how AI is actually great or actually awful, but I was hoping to have more conversations like this in the comments. I'm glad I can help people feel better.
What did you set the context window to? That's been my main issue with models on my macbook, you have to set the context window so short that they are way less useful than the hosted models. Is there something I'm misisng there?
Has happened to me before. It seems they change anything that has a negative connotation to try to take something more positive out of it. I don't love that they do that without asking or confirming with the author. But this title is also fine with me. I actually thought about naming it "Curing your AI 10x Imposter Syndrome", but it felt like a stretch that someone would understand what the content would be about.
I think I may have worded this poorly. I mean the total amount of code review time that goes into 3 months of work (likely on hundreds of PRs) can't be compressed into 1.5 weeks at the same portion of time being allocated to code review. Each code review has a "floor" time, a minimum amount of time loss due to context switching, reading, writing, etc.
I'm happy to hear that! I hope you felt seen by this line from the article:
> Oh, and this exact argument works in reverse. If you feel good doing AI coding, just do it. If you feel so excited that you code more than ever before, that's awesome. I want everyone to feel that way, regardless of how they get there.
100%. It's made me like dev again because my head can be used for things other than remembering arcania - this may be a curse of using languages like Ruby and Elixir which mostly don't have great tooling.
I enjoyed the article, fwiw. Twitter was insufferable before Elon bought it, but the AI bro scene is just...wow. An entire scene who only communicate in histrionics.
I mean throughput, not latency. As in if you ship 10 meaningful changes in a month before you now ship 100.
My point around waiting for things like code review is that it creates a natural time floor, the context switching takes time and slows down other work. If you have 10x as much stuff to get reviewed, all the time loss to context switching is multiplied by 10x.
With terraform, using a property or a resource that doesn't exist is effectively the same as an API call that does not exist. It's almost exactly the same really, because under the hood terraform will try to make a gcloud/aws API call with your param and it will not work because it doesn't exist. You are making a distinction without a difference. Just because it can be caught at runtime doesn't make it insignificant.
Anyway, I still see hallucinations in all languages, even javascript, attempting to use libraries or APIs that do not exist. Could you elaborate on how you have solved this problem?
> Anyway, I still see hallucinations in all languages, even javascript, attempting to use libraries or APIs that do not exist. Could you elaborate on how you have solved this problem?
Gemini CLI (it's free and I'm cheap) will run the build process after making changes. If an error occurs, it will interpret it and fix it. That will take care of it using functions that don't exist.
I can get stuck in a loop, but in general it'll get somewhere.
