bruh, 20k usd in tokens, god knows how much electricity and stolen work for training, precise testing suite optimized for Claude, a problem solved tens of thousands of times before all in training data, yet non-optimized compiler barely compiling stuff but no proof that they can even run for simple programming language.
@troi@techhub.social tbh I could see people who are considered good programmers in one place but not in another place (just prompting to get things done with minimum effort & reserving the effort for something else).
Probably it comes back to interest & care, how much the person is interested in iterating over their solution & architecture + learning things regardless of seniority level to achieve a higher level goal (simpler design for example rather than stopping when it works). Maybe that could be an indication of a good programmer?
the same reason a person gets 40 year prison for having CP materials (rightefully so), but politicians and billionaires are all straight up pedos going for trafficked minors in an island get a comfy government cover up
bruh, so it's not me who was stupid all this time for not being able to put an estimate for large initiatives. It always feels forced to give an estimate.
It has been really fun watching any LLM debugging a bug in a moderately large codebase. It has been so bad in my experience (I really wanted the hype to be real) even in really simple and readable programming languages.
It doesn't stand a chance though for more complex languages. There was an obvious bug in the way one Rust project was loading a config, decided to "test" Claude sonnet 4.5, I watched it identifying the issue but over engineering paragraphs of new Rust utilities without getting there while the solution was in the second paragraph of the github repo of config-rs, just adjusting the prefix and dropping the separator entry.
First time I have heard about such concepts was 2015 for my phd studies. Radar imaging, through the wall imaging, it introduced me to the large math framework of inverse and ill-posed problems.
That's a solid point. Even if it looks great (most of the time not). I try to build small predictable parts, refactoring, ... Even with all precaution, I find tech debt hidden somewhere weeks and months later.
I use LLMs extensively for work as people think we are faster now but try to avoid letting LLMs write anything for personal projects.
bruh, 20k usd in tokens, god knows how much electricity and stolen work for training, precise testing suite optimized for Claude, a problem solved tens of thousands of times before all in training data, yet non-optimized compiler barely compiling stuff but no proof that they can even run for simple programming language.