Live data from Hacker News

You can't unit test for taste

dev.karltryggvason.com

51–60 of 157 posts

Re: You can't unit test for taste

#51
post #36

Earlier quoted context omitted.

I remember reading an interview with a fireman who described a time when his buddy evacuated a team because he "felt" that a floor would collapse imminently. He couldn't articulate why but they trusted his gut and it did collapse. A lot of software engineering relies on that kind of intuition and on a good team you can integrate it and benefit from it and avoid all manner of floor collapses.

To play devil’s advocate, intuition is still a physical response to stimuli mixed with knowledge of past experience. Hypothetically it could be modeled- the problem here comes down to how to encode it.

"Encoding" implies some GOFAI symbolic formal rule machinery.

I'd argue that transformers are a pretty good indication that intelligence isn't "encodable" in the way we think it means. Usually, most "model" vocabulary means that we can explain and constrain the "data" from the "rules". Except the mere "data" is trillions of interacting weights.

That may be encoding in a physical sense, but that still doesn't explain the intuition in any legible way to humans.

Cynically, we've been able to encode everything already by just saying everything's a transition in a huge lookup table. Not very informative though.

Re: You can't unit test for taste

#52
post #15

Language 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...

Cool! Thanks for sharing.

Re: You can't unit test for taste

#53
post #4

You 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…

[flagged]

Re: You can't unit test for taste

#54

Earlier quoted context omitted.

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.

Wouldn't this style of training suffer from the AI learning things the user didn't intend? I may thumbs down something for a specific detail I don't like, while other things in it are great. Certain traits that tend to occur together go along for the ride. We see similar things happen in natural selection, where mates may be chosen for 1 specific feature, and other less desirable things come along for the ride. Outsi…

This can usually be solved by scale alone (in all three contexts: RL, evolution, and IRT / psychometric testing)

The co-occurence thing is often not a bug of the algorithm but a genuine part of the stochastic landscape that must be solved. Evolution isn't "failing" when sickle cell vulnerability is ported along with malaria resistance; it's just a real tradeoff being made in the current biological landscape.

Re: You can't unit test for taste

#55

Earlier quoted context omitted.

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.

This is RL, right? Like, this is exactly why models have mostly converged around obvious style, because we train them literally on thumbs-up/thumbs-down data of what good behavior and good code looks like. And that's why it's so hard to get a model to reproduce the specific taste of a person or an organization. My taste is different than yours, so if we dump our aggregate preferences into RL, in averages out to nothi…

It’s supervised learning rather than RL, you’re just training to labels. It doesn’t work (doesn’t generalize) because there is no guarantee or even expectation that any causal relationship is learned, it’s just whatever convenient pattern gets the lowest loss. There is lots of research on this for those unaware.

Re: You can't unit test for taste

#56

Earlier quoted context omitted.

This is RL, right? Like, this is exactly why models have mostly converged around obvious style, because we train them literally on thumbs-up/thumbs-down data of what good behavior and good code looks like. And that's why it's so hard to get a model to reproduce the specific taste of a person or an organization. My taste is different than yours, so if we dump our aggregate preferences into RL, in averages out to nothi…

This is, in short, the big current problem with AI. LLMs are built for scale so they've given up on the kind of online learning / "long term memory" processes that would individualize them. The LLM is permanently locked to being a really cracked engineer on their first day at your company, looking at your codebase for the first time. You can scaffold a bit with .md files, but at the moment they lack the ability to do…

Yea, individual learning is super expensive at this point and scale is the only way for paying for training at this point. Maybe at some point in the future we'll get this.

Re: You can't unit test for taste

#57
post #27

Exactly one of the reasons I never went down with all the TDD dogma of only writing code to fix broken tests. There is a reason conference talks are always about plain algorithms and data structures.

yup and I find it weird that people still remain so defensive of the Church of TDD even against empirical studies that show its limited benefits

https://arxiv.org/abs/2602.07900

Re: You can't unit test for taste

#58
post #23

Earlier quoted context omitted.

> Rick Rubin told Anderson Cooper he has no technical ability. Doesn't play instruments. Can't work a mixing board. If you watch his interview on Rick Beato's channel, this myth will fall apart. He plays guitar, had his own punk rock band and his guitar playing is featured on some high-profile records he produced. Also, he has a lot of practical experience with all kinds of studio equipment.

That’s exactly it. His taste isn’t in any one thing. It’s the esoteric and accumulated from a variety of things. You can’t package it up. That’s the point on the project specs. I can never get it right in one, but the arc over 100 becomes visible. Especially to an LLM that has the capacity to intake and understand that.

>You can’t package it up.

Well, you can package it up, otherwise Rick wouldn't exist.

Re: You can't unit test for taste

#60
post #4

You 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 cannot externalize taste. You could perhaps mimic someone’s taste, but that’s not the taste. Knowing the taste requires actually tasting it. You can’t capture the taste, it’s already gone.

[dead]
Post reply on HN