jessoteric

> I'm building The Operating System for SMBs

it's a genius

i've also been using opus 4.5 with lots of heavy rust development. i don't "vibe code", but lead it with a relatively firm hand- and it produces pretty good results in surprisingly complicated tasks.

for example, one of our public repos works with rust compiler artifacts and cache restoration (https://github.com/attunehq/hurry); if you look at the history you can see it do some pretty surprisingly complex (and well made, for an LLM) changes. its code isn't necessarily what i would always write, or the best way to solve the problem, but it's usually perfectly serviceable if you give it enough context and guidance.

> Of course, you can declare that the world itself is inherently sinful and imperfect, and is not ready for your beautiful theories

i see we are both familiar with haskellers (friendly joke!)

i find it's pretty rare to have a project that only consists of one or two languages, over a certain complexity/feature threshold

IME this has been significantly reduced in newer models like 4.5 Opus and to a lesser extent Sonnet, but agree it's still sort of bad- mainly because the question you're posing is bad.

if you ask a human this the answer can also often be "yes [if we torture the library]", because software development is magic and magic is the realm of imagination.

much better prompt: "is this library designed to solve this problem" or "how can we solve this problem? i am considering using this library to do so, is that realistic?"

That seems like a good idea... hmm.

This right here. Every time I talk to someone claiming 2-4x multipliers, after a few rounds of conversation they eventually admit "yeah you have to learn when to stop when it's no longer productive, you get a feel for when it's veering into wasting your time".

It can't be both. It can't be 2-4x multiplier _and_ be wasting your time to the extent that you have to "get a feel for when it has been wasting your time".

the main issue is that you end up looking down the barrel of begging claude, for the fifth time this session, to do it right- or just do it yourself in half the total time you've wasted so far.

at least, this is what i typically end up with.

isn't the issue that sometimes a given scanner can't know from where the package is sourced?

like if I'm scanning an arbitrary linux system, and I see `libssl.so.1` but I don't see it in the local package manager, I don't really have an option other than to call it generic.

I do agree that "generic" seems to be WAY overused though. Maybe tools that report on SBOMs, like FOSSA or whatever, should emit warnings to users about "generic" PURLs.