spectrums_coherence

LLM is very good at programming when there are huge number of guardrails against them. For example, exploit testing is a great usecase because getting a shell is getting a shell.

They kind of acts as a smarter version of infinite monkey that can try and iterate much more efficiently than human does.

On the other hand, in tasks that requires creativity, architecture, and projects without guard rail, they tend to do a terrible job, and often yielding solution that is more convoluted than it needs to be or just plain old incorrect.

I find it is yet another replacement for “pure labor”, where the most unintelligent part of programming, i.e. writing the code, is automated away. While I will still write code from scratch when I am trying to learn, I likely will be able automate some code writing, if I know exactly how to implement it in my head, and I also have access to plenty of testing to gaurentee correctness.

I see you don’t run electron app in flatpaks :)

I think he has repo pre ChatGPT with legitimate usecases, while that would not be a conclusive proof, I cannot imagine some chatbot would bother with this.

This dude need to chill, he also pushed the systemd change, and in his blog he seems to believe android “advance flow” for sideloading protects users.

The one they are targeting is California’s AB-1043, which still have three quarters of a year before it comes into effect…

I think this dude might get too excited for his new subscription of claude code or whatever, and decided to spam every project with these request. Some of these are reasonable, some are compliance in advance.

Also this dude writes two freaking blog every week with LLM. If I were him, I would try to find some joy in my personal life…