I've had a similar experience, shipping new features at incredible speed, then waste a ton of time going down the wrong track trying to debug something because the LLM gave me a confidently wrong solution.

Well that's kind of on you for not noticing that it was the wrong solution, isn't it?

Sometimes the solution is 99% correct but the other 1% is so subtly wrong that it both doesn't work and is a debugging hell.

Welcome to programming.

I think the parents post happened to everybody, and if it hasn’t it will.

The edge between being actually more productive or just “pretend productive” using large language models is something that we all haven’t completely figured out yet.

often it's something you casually overlook, some minor implementation detail that you didn't give much thought to that ends up being a huge mess later on, IME

Ya but you kind of get painted in corner sometimes. And sunken cost fallacy kicks in.

It's on you however for not understanding the greater point?

Seems like LLMs would be well suited for test driven development. A human writes tests and the LLM can generate code passing all tests; ending with a solution that meets the humans expectations.

This is more or less how I use LLMs right now. They’re fantastic at the plumbing, so that I can focus on the important part - the business and domain logic.

I disagree because you're only considering the "get code to make the test pass". Refactoring, refining, and simplifying is critical and I've yet to see this applied well. (I've also yet to see the former applied usably well either despite "write tests generate code" being an early direction.)

> UCNP heterostructures present a stringent test for any new DL model and representation.

Are UCNP heterostructures also the most promising area of application, or are you looking to apply the method in other areas now that you've validated it in the stringent case?

How do you read it though? I tried but felt like I'm lacking a lot of context without which it doesn't make much sense.

I started another just last week: https://github.com/sumnerjj/bookmarkstorage2

Fascinating!

> anyone with a lick of python can generate millions of workouts

Are you offering an API for the workout generator?

Any plans to generate workout plans for a week/month and incorporate rest days?

Not saying it's nice, but that just sounds like tough negotiating to me. As opposed to actual illegal salary collusion by Apple, Google, Intel, Adobe

Stall for time: repeat what the other person said back to them, reframe the questions, state the obvious, use filler words, etc. Say stuff mindless enough that you can think about the real problem while talking.

How do you test for curiosity?

Curiosity and ego seem to be inversely correlated.

If you ask relevant but technically hard and esoteric questions _without the expectation of an answer_ you can sometimes see it in the manner of the response. Do they probe the question? Do they explore the idea, even if they don't know the answer? Do they readily admit that they don't know?? Or do they become defensive? Do they fake their way through it? If they make a mistake and you point it out, how do they respond?

You take the person off the beaten path in the interview.

> How do you test for curiosity?

uh? tell me more

Must be the quality of the fiber

touché

> everyone

Do you really think the proportion of people who care about those issues is greater inside these companies, compared with the general population? Or is the proportion of people roughly the same, but they only speak up about it because those are the issues the company is involved with?