[potatolicious]

What you're getting at is the heart of the problem with the LLM hype train though, isn't it?

"We should have rigorous evaluations of whether or not [thing] works." seems like an incredibly obvious thought.

But in the realm of LLM-enabled use cases they're also expensive. You'd need to recruit dozens, perhaps even hundreds of developers to do this, with extensive observation and rating of the results.

So rather than actually try to measure the efficacy, we just get blog posts with cherry-picked example of "LLM does something cool". Everything is just anecdata.

This is also the biggest barrier to actual LLM adoption for many, many applications. The gap between "it does something REALLY IMPRESSIVE 40% of the time and shits the bed otherwise" and "production system" is a yawning chasm.

[marcosdumay]

It's the heart of the problem with all software engineer research. That's why we have so little reliable knowledge.

It applies to using LLMs too. I guess the one largest difference here is that LLM has few enough companies with abundant enough money pushing it to make it trivial for them to run a test like this. So the fact that they aren't doing that also says a lot.

[oblio]

> What you're getting at is the heart of the problem with the LLM hype train though, isn't it?

> "We should have rigorous evaluations of whether or not [thing] works." seems like an incredibly obvious thought.

Heh, I'd rephrase the first part to:

> What you're getting at is the heart of the problem with software development though, isn't it?

[simonw]

The UK government ran a study with thousands of developers quite recently: https://www.gov.uk/government/publications/ai-coding-assista...

[redhale]

I don't necessarily think the conclusions are wrong, but this relies entirely on self-reported survey results to measure productivity gains. That's too easy to poke holes in, and I think studies like this are unlikely to convince real skeptics in the near term.

[b_e_n_t_o_n]

Woah, finally something with actual metrics instead of vibes!

> Trial participants saved an average of 56 minutes a working day when using AICAs

That feels accurate to me, but again I'm just going on vibes :P

[troupo]

Before you get into the expensive part, how do you get past "non-deterministic blackbox with unknown layers in between imposed by vendors"

[potatolicious]

You can measure probabilistic systems that you can't examine! I don't want to throw the baby out with the bathwater here - before LLMs became the all-encompassing elephant in the room we did this routinely.

You absolutely can quantify the results of a chaotic black box, in the same way you can quantify the bias of a loaded die without examining its molecular structure.