Have you considered using quickcheck/random/property-based testing with LLM code generation to automate function implementation?

Yeah, I've already looked into it, but decided to keep developing it "example driven" for now. Aka I'm playing around with it, and whenever I find something that's broken I keep a note of it and then I pick those notes one by one and implement them. Once the most common things are implemented I will start writing property tests to catch all the edge cases of each feature.

I'm saying you can go even further and automate the entire thing using LLMs/agents, it is pretty much the ideal use case: you have a black-box reference implementation to test against; descriptive documentation for what the functions should do; some explicitly supplied examples in the documentation; and the ability to automatically create an arbitrary number of tests.

So not only do you have a closed loop system that has objective/automatic pass-fail criteria you also don't even have to supply the instructions about what the function is supposed to do or the test cases!

Obviously this isn't going to be 100% reliable (especially for edge cases) but you should be able to get an enormous speed up. And in many cases you should be able to supply the edge case tests and have the LLM fix it.

(Codex is still free for the next few days if you want to try their "High"/"Extra high" thinking models)

How is the popularity/rank in functions.csv determined?

That's actually a value that Wolfram determines themselves. Here is the documentation for it: https://reference.wolfram.com/language/ref/WolframLanguageDa...

Here is e.g. all the values for the Plus[] function:

$ wolframscript -code 'WolframLanguageData["Plus", "Ranks"]' {All -> 6, StackExchange -> 8, TypicalNotebookInputs -> 5, TypicalProductionCode -> 6, WolframAlphaCodebase -> 6, WolframDemonstrations -> 4, WolframDocumentation -> 4}

No, the difference is that the government agrees to no "unlawful" use as determined by the government.

Anthropic said that mass surveillance was per se prohibited even if the government self-certified that it was lawful.

No, the difference is that the government agrees to no "unlawful" use as determined by the government.

Anthropic said that mass surveillance was per se prohibited even if the government self-certified that it was lawful.

It feels like gnu parallel with --transfer-file would have solved this problem

Their first example is bad:

    ps aux | grep nginx | grep root | grep -v grep

can be done instead (from memory, not at a Linux machine ATM):

    ps -u root -C nginx

which is arguably better than their solution:

    psc 'process.name == "nginx" && process.user == "root"'

The commands in their example are not equivalent. The ps | grep thing searches the full command line including argument while ps -C (and, presumably, the psc thing) just returns the process name.

Should you for some reason want to do the former, this is easiest done using:

  pgrep -u root -f nginx

which exists on almost all platforms, with the notable exception of AIX.

Their other slightly convoluted example is:

  psc 'socket.state == established && socket.dstPort == uint(443)'

which is much more succinct with:

  lsof -i :443 -s TCP:ESTABLISHED

Many new tools appear because people don't know how to use the existing tools or they think the existing tool is too complicated. In time the new tool becomes just as, or more, complicated than the old tool. Because there is a reason the old tool is complicated, which is that the problem requires complexity.

It has process.cmdline as well as .name

“ss” also has filters, no need for grep

ss -o state established '( dport = :ssh or sport = :ssh )'

Number 1 on the front page of Hacker News for explaining how to connect to a remote machine via ssh.

I too am dumfounded by this. Is it an off day? Have all the people that actually know how to do things with computers gone somewhere else? What is going on here?

It's all AI hype bro sycophants for the most part now. Oh, well.

Yeah I feel like I'm missing something here. I'm not sure if people being so dependent on these LLMs generating code is that widespread at this point or if this is some kind of publicity stunt.

That plant is subject to regulation and the xAI turbines evade regulations by claiming they are "portable".

That plant is subject to regulations. The xAI turbines have evaded regulations by claiming that they are portable.

You're not very off the the mark. To add in that extra detail, xAI is using portable gas turbines that are meant for providing emergency backup power in case of a catastrophic loss of power, like in the event of a natural disaster. Being portable, they lack the systems necessary to avoid polluting the surrounding air with oxides of nitrogen and formaldehyde - really nasty stuff. That shouldn't normally cause a serious issue, since the turbines are meant for temporary backup alone. But at Memphis, xAI is stretching the meaning of 'temporary'.

What is the difference between 3rd party skills and connectors? How do you access/install 3rd party skills in claude code?