[trjordan]

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 know and hand it to a machine, I'd do that, but it impossible.

People aren't books or hashmaps. If you want to build something, you need to use the tools, not teach the tools to use you.

[edit: I'm trying to figure out if there's something to be done about this. Email me if you want to chat -- tr at tern dot sh]

[giancarlostoro]

What's kind of funny is this is how I implemented "gates" for the ticketing system I built for Claude, because Beads would just close tickets without validation. I have tickets that are literally "Human validation" tier, so it will work on the next available thing until I personally tell the model to close it. So, in that spirit, yeah, you can unit test for taste, if you implement external validation.

Unit test runs, waits for human input before passing or failing, which might seem out of the norm, but we already have QA do manual testing.

[bonzini]

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 people what they need to know.

But for taste of the kind described in the article there's not even a definition. The logic ended up being "trust a bunch of opaque weights the most"

[Chris2048]

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.

[Dumblydorr]

Randomized trial. Half of them pledge to use AI freely and liberally, half of them to never use it, compare via surveys and off-AI tests after X months. Could even flip it so then the non-users used it for X months and vice versa, see if losses/gains are stable.

[eithed]

I agree and indeed externalize everything you know *that matters*.

Want to follow certain pattern, or convention - define it, ie active record vs repository pattern, stick is as an ADR! You don't know what you want? Look at what Claude produces and then acquire taste, mark this as convetion that future sessions will follow, but stick to *one* convention!

[delichon]

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.

[trjordan]

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 nothing interesting.

For the code-writing case, this means you end up reviewing every line of code, looking for places where you'd thumbs-down the code. Not every line of code contains a real decision, though, so it feels like a waste of time.

[eithed]

Yes and no.

If I were to ask you - what convention you want to follow for your database columns - camelcase or snakecase? There's no correct global answer. There's no overarching truth that should apply to all databases in existence (even if you'll focus on a certain type of database). Hence the no.

But yes, because in the context of existing system there is a convention. If it's snakecase, you create new tables with snakecase column names.

LLMs will generally follow conventions, but sometimes they will not, because indeed - global truths sometimes win over (I assume)

[paytonjjones]

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 what humans do: go to sleep, encode things from short to long term memory, and wake up the next day with more specific knowledge baked in.

[trjordan]

100%. The problem with them isn't making sure they're doing the right thing, it's making sure they're not making bad assumptions.

IMHO this is where code review goes until we fix the individualized model thing: you need to review the decisions the agent made, where you didn't steer. Most will be right. A few will be disastrously wrong. But decision-by-decision is a lot less to review than line-by-line of code.

[plastic-enjoyer]

> LLMs are built for scale so they've given up on the kind of online learning / "long term memory" processes that would individualize them.

I wonder if this is even desirable from a product perspective. You probably don't want online learning in a product that you are selling because you can't guarantee a consistent quality of the product.

[paytonjjones]

You could say the same thing about employees!

And to be fair, the ability to fire employees and hire new ones is pretty important for that reason. In cases where you can't easily fire employees (e.g. unions), you encounter the very problem you're describing, and it often leads to companies preferring more consistent automations.

[al_borland]

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.

Outside of AI, I run into this issue when taking basic personality tests. A question may be written for a specific reason, which influences the results, but the reason for my answer may be completely unrelated to the reason intended by the person who made the test.

[paytonjjones]

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.

[punnerud]

If you have enough examples you can train an AI on your preferences, then use that distilled AI as a unit test. Don’t combine multiple into one AI. If they don’t agree you want it to fail so you can decide and retrain the tests.

[tmoertel]

> 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.

I'm not so sure. For instance, you can write down what it means for a program to be free of XSS and other injection vulnerabilities. Now, how would you unit test for that property?

[deadbabe]

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.

[pydry]

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.

[dyarosla]

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.

[sigbottle]

"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.

[sigbottle]

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 <arbitrarily hard unspecified thing that is basically unfalsifiability>". (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)