soon_to_be_sb

> tends to come from the AI being very thorough about ensuring the code does exactly what’s expected..

So terse and flexible code can't be made to do exactly what is expected?

What was the gist of their argument?

Am I?

Tell me again where there is NO widespread automatic consensus about how imperative is that one HAVE TO use these things from a sandbox?

The last time this happened was when the whole world agreed that it is alright to take a device with multiple cameras, mics AND 24x7 internet connectivity to our most private places...

>we'll recalibrate eventually based on understanding what level of abstraction we can operate on...

This would be at the level of helper functions < 10 lines of code.

Every once in a while something comes up that proves beyond a doubt that 99% of human beings on planet earth cannot think for themselves. And most sensible things that human beings do, they do by following the herd or "instructions".

One that is has not issued shares.

Where can I read more about this!?

Thank god if true, but dependence on LLMs is not great for the developers. At least good thing for the end user.

So you are saying that it was bad because of what arguments it made?

> Ignoring the 99.99% of titles

Point is that you can't ignore well marketed slop. It will show up everywhere. Volume of slop matters because that drags down the median quality so that it becomes feasible to market slop and get returns on it.

It is not that I expect it. But instead, it is just about being realistic about how real world projects differ in workflows and conventions. If what you describe is not available, then the next best thing is to make the reviewer aware of the context and solution by means of small commits with sensible descriptions.

What did the 5G book talked about and why was it bad?

>act like "slop" never existed before 3 years ago.

Volume matters lol..

Goodhart would beg to differ...

>society is so insensitive to actual quality that it will reward slop to the tune of a millions dollars, the the problem lies with that, not her.

If the society is so dumb that it does not deserve to survive, then so be it.

Are you up for that line of thought?

>writing about 5G, memories of Water and other garbage.

Have you actually read some of these garbage? If not, how do you decide it was garbage?

>without out of band discussions..

Not every project can afford this.

>With such knowledge, it’s easy to glance at the code and understand the implementation.

I really doubt that this is true for large, legacy code bases, where one is only familiar with a small part of the system.

What you are saying is true if created manually. It is a chore to create sensible commits messages when you are committing often.

But LLMs appear to be pretty good at making small commits with sensible commit messages, that greatly help to make sense of the whole PR.

Regarding large monolithic commits, how do you even know where to start reviewing in a large PR? Smaller commits at least give you some sense of ordering.

Imagine that I am working at the AI company, and my friend has some bone to pick with you. My friend asks me to ask your AI agent to put some unsafe photographs/videos in your computer and do what ever necessary so that it looks like you put those files there.

Then my friends tips off the cops. And your life disappears! Gone!

And you didn't get a chance to share your story because I don't think you ll have wifi where you would be going, and frankly you are too clueless to imagine your AI agent doing something like that...

10 millions developers doing something stupid does not make it right!

>A Merge Request or Pull Request is the only thing that makes sense to review, and always has been since before LLMs.

Why doesn't it make sense to review smaller units of change within a big PR?

>> "I take an object, I put it on the table, and I push the table... there's no text in the world, I believe, that explains this... your GPT-5000, or whatever it is, it's never gonna learn about this."

As far as I know, those things are still true. Unless there is text in the training material that the text in the prompt can map to, or there is text in training material that describe how to map text in the prompt to text in the training material, LLMs cannot process the prompt.

So may be he is wrong about what could be in the training material. But I don't think he is wrong in the fundamental..

This is sort of what I mention in my original comment. These claims, when pushed, turns out not to hold water...

>LLMs won't be able to do this or that) turned out to be wrong

Where can I read more about this? I have seen people make this claim for a while, and when I looked deep, it used to turn out to be wrong.

Why bring that (anti-blah blah blah) up at all. What is your point? I don't get it..

> Antivax influencers, though, are doing it out of the goodness of their hearts.

Made no such claim. Why are you responding to something I didn't mention?

How about giving a shit about efficiency?

>We've done this for decades..

"We" do it because governments want to reduce the cost managing an outbreak. Not because it is good for everyone who takes it in some absolute sense. I mean, such measures are enforced without taking effort to assess individual RoI, because that would be more costly than managing the outbreak.

Governments and establishments ("We") don't give a shit about your health beyond your ability to vote and pay taxes.

> LLM adoption is only going to monotonically increase

Yes, but the question is "what kind of adoption"? The kind that just unleashes it, or the kind that put it on a short leash.

There is a point in the LLM usage spectrum where I feel that I am not really understanding the stuff I am creating. I can have the LLM write some code, without starting to feel this. But it is only a small amount of code...

> empowered people to be more decision makers, lead developers, architects

Add a "pseudo" before each and we would be in total agreement.