Federal judges and SCOTUS have some times ruled in favor of states or in favor of the federal government with the 10th amendment being at the center of an argument
There's no fundamental reason that I have to read random blogposts from people I don't know. I do it today because I find it to be an enjoyable way to learn more about my profession and explore various perspectives on it. If I stop finding it enjoyable because too many people write their posts with AI, I'll stop reading these kind of blogs altogether, in the same way that I (and I suspect many commenters here) do not read even the most lovingly crafted Linkedin posts.
The written word is how people interact with LLMs. Clarity and precision in writing results in more effective prompting of LLMs. It is just as possible that leaning heavily AI writing will be seen as a marker of not being natively skilled enough at writing to prompt LLMs effectively because of the GIGO principle.
When AI generates code, we have the ability to easily verify it and test it.
The same is not so easy with free form text. I have been thinking about this mainly around when agents write plans or edit plans, but I think figuring out how to do this in general would be a huge breakthrough.
Logical English was one idea I came across and Runcible https://runcible.com/ was another idea I recently stumbled on.
It couldn't run "hello, world" on systems where the include files were not located in the directory that it expected -- producing instead diagnostics saying, quite clearly, that the header files were not found. On systems where they were, it built versions of postgresql, redis, and several other things which passed their test suites completely.
If you've heard this problem described as a fundamental limitation of the compiler, and not the kind of packaging glitch that's routine to find in pre-alpha software of all descriptions, whoever described it to you that way is not serving their readers well.
I'm not saying CCC was production-ready, or close -- the total lack of an optimizer would be a killer in any real use, and I assume that there were problems with the diagnostics at least as bad as problems with performance and the include files, for similar reasons -- the LLMs hadn't been asked to optimize for that stuff yet, just test suite correctness. But it did achieve that, and the amount of cope I've seen on social media claiming otherwise is more than a bit disturbing.
I have a colleague who multiple times committed code that doesn't work, like at all. Why? His code is only used in tests but not in the actual application. And apparently he never even bothered to click through things even once, let alone reviewing the code.
If it doesn't work, it doesn't. You can find all these excuses. But at the end of the day, there is a difference between an end user being able to get something out of your code or not.
i think theres a different lesson to be taken from those cases - the LLM will build to what you give a feedback loop for.
if you give just the logical tests, it wont consider the speed at all. if you included tests that measure the speed and ask the llm to match the performance, itll do that too.
its the same class of error as everything else with llms. it has no common sense context for things people consider important. if you dont enforce the boundaries, it will ignore them
The intro was the best part of the README in my opinion.
The rest of the README looks and feels AI generated. I am guilty of this same thing with README files.
I have been using Go since 2014. I have services that just run without issue.
Having backwards compatibility with 1.0 just makes it easier to maintain software.
The big plus in the modern era is that the simplicity of the language lends to having agents write Go without much fuss. That and the standard library being batteries include lets you direct the agent to use little or no third party dependencies.
reply