I like to think of testing as making sure things not wrong, but not making it right.
Working, useful, delightful, in that order. Testing can make things more likely to work, that's it.
You can't unit test for taste
11–20 of 157 posts
Re: You can't unit test for taste
#12Taste is mostly the part of the spec you forgot to write down, plus the part you couldn't write down even if you tried.
Re: You can't unit test for taste
#13You can't unit test for taste if you haven't written down what you mean by taste. If you can externalize it, then you can. Follow this line of thinking, and the AI-friendly answer is easy: we just have to externalize everything we know, so Claude can implement what I want. Except that I can't fully externalize myself. Debugging a system takes more resources than running the system. If I could write down everything I…
It can't be written down as code, that's the point. I am more familiar with taste in coding and it can at best be described—that the resulting code is too subtly different from something else in the codebase, that you're masking a different bug, that you're not following what the code tells you. The good part is that while this cannot be unit tested, you can write documentation and code comments about it that tell pe…
Technically, AI is code, just very complex code.
I'd say there are "simple" simple things you can do though, like take automated screenshots and detect colours for jarring colourschemes.
Re: You can't unit test for taste
#14We can encode taste -- generative AI depends on it. Ask people to compare two examples and pick the one with better taste. You can even ask them to rate multiple subjective criteria at once. Use that to learn a scoring function based on the rating labels, and raw features. Now you can write tests.
Re: You can't unit test for taste
#15Language count is a decent notoriety signal though pretty coarse. The OP/author should take a look at QRank: https://qrank.toolforge.org/
> QRank is a ranking signal for Wikidata entities. It gets computed by aggregating page view statistics for Wikipedia, Wikitravel, Wikibooks, Wikispecies and other Wikimedia projects
from https://github.com/brawer/wikidata-qrank/blob/main/doc/desig...
Re: You can't unit test for taste
#16[dead]
Re: You can't unit test for taste
#17You can't unit test for taste if you haven't written down what you mean by taste. If you can externalize it, then you can. Follow this line of thinking, and the AI-friendly answer is easy: we just have to externalize everything we know, so Claude can implement what I want. Except that I can't fully externalize myself. Debugging a system takes more resources than running the system. If I could write down everything I…
You may be able to effectively externalize taste by "hot or not" style pair testing. Enough comparisons and I'd expect ML to be able to mimic human taste by latching on to features we're not well aware of influencing us.
Re: You can't unit test for taste
#18So now we need a framework for unit tastes
Re: You can't unit test for taste
#19https://pureinference.com/insights/taste-is-the-new-skill
I wrote about this a few months back. Rick Rubin is famous for this. I do think it is something that can be trained though, it just needs a lot more context. Taste builds over time through lots of unit tests, through lots of content writing, through an accumulation of product decisions. It’s hard to put it in the individual spec, but it can be teased out of 100 project specs. And when you get to that scale the AI starts to do it pretty well.
Re: You can't unit test for taste
#20You can't unit test for taste if you haven't written down what you mean by taste. If you can externalize it, then you can. Follow this line of thinking, and the AI-friendly answer is easy: we just have to externalize everything we know, so Claude can implement what I want. Except that I can't fully externalize myself. Debugging a system takes more resources than running the system. If I could write down everything I…
Exactly. Every single philosophical statement in history runs up against the issue where you can just say, "yeah, it's pretty much this. You just need to do ". (Including this one)
And maybe that's just our limits with philosophy, modeling, assumptions, whatever. The danger is not realizing when we're in that zone.
(Fwiw I think unfalsifiability is a limit with any system - "you didn't compile in my syntax/semantics" is an gotcha that's actually valid and useful, but nobody can really determine the hard line)