When you look at GPU compute at any site, there is not much help to understand what kind of powerful you are actually renting. I think the worst thing is that some providers has "cheap" gpus, but they are so old that using them is directly counterproductive since it does not support any of the new features that makes GPUs fast.

Google will show a Nvidia T4 in Colab and also Google Cloud, but it is actually from 2018 and does not support BF16 or FP8. You are essentially renting outdated hardware. They will also rent you a L4, but it only has 300 GB/S memory which is really slow compared to newer GPUs, so all in all you are underselling your own time by renting one of those cards, even though it looks like a great getting started cards. And don't get me started on the P4 which they are selling at $438 a month.

Using Claude Code and alike with each agent working in a tab in the terminal feels very productive. You spend very little time waiting for AI since you basically start a task and go look at the next agents output.

But with this workflow for 6 months I can now see the downsides:

Finishing software is much harder

Working on 3-4-5 different features at the same time means you work in parrellel but you move slower on a single feature. It feels incredible moving on that many features, but it is harder to finish each. To finish a feature you need to deploy it and test it in the end, making sure it actually works.

I don't think we will see the exponitial boost from AI before AI can code itself.

AI is incredible useful, it is incredible at writing a lot of code with high accuracy, but when you use AI to code with, it gets the basic things incorrect.

Missing Plan mode

It is weird that gemini cli has no plan mode. In Claude Code you can do plan mode with two shift tabs, and it makes Claude present a plan after some investigation.

Less readable output in Gemini

Gemini

I am using Claude Code myself and there is people talking about that AI Coding agents just don't live up to standards, that it misses stuff and does not follow instructions, making it daunting to work with it. You can see it here AI Coding Sucks on youtube.

I can relate, using Claude Code now for 5 months, it does not sees to amaze how often it falls through and does simple things wrong.

Still helps

But I am using coding agents still because it helps me type less still, in programming when running commands from the commandline even 1 character wrong makes a mistake. This mistake the coding agent never makes, it does not mistype by one character.