autobodie

If the prompt is good, the LLM will tell you when it's wrong, but you can use production testing if necessary like Tesla.

When I do that, they come back with something more simple than before but either wrong or still unnecessarily complex.

Over the past week, I have been writing a small library for midi controller I/O and simple/elegant is the priority. I am not really that opinionated. I just want it to not be overengineered. AI has been able to make some suggestions when I give it a specific goal for refactoring a specific class, but it cannot solve a problem on its own without overengineered solutions.

More often, LLMs give me wildly complex and over-engineered solutions.

Profit over security, outsource liability

It's a lot of meandering and mundane analogies that don't work very well or explain much, so it's totally understandable that so many people have different interpretations of what he's even trying to say. The only consistent takeaway here is that he's talking about using AI (of many sorts) alongside legacy software.

I don't think people are misinterpreting. People just don't find it convincing or intriguing.

Objectivity is lacking throughout the entire talk, not only in the thesis. But objectivity isn't very good for building hype.

If so, that certainly fits with my experiences.

"Behold the impeccable nuance of my opinion"

My experiences so far suggest that you might be right.

Why use AI to do something so simple? You're only increasing the possibility that it gets done wrong. Multi-cursor editing wil be faster anyway.

Haha, doing this with AI will bury you in a very deep hole.

I think that's wrong. I only have to write code once, maybe twice. But when using AI agents, I have to read many (5? 10? I will always give up before 15) PRs before finding one close enough that I won't have to rewrite all of it. This nonsense has not saved me any time, and the process is miserable.

I also haven't found any benefit in aiming for smaller or larger PRs. The aggregare efficiency seems to even out because smaller PRs are easier to weed through but they are not less likely to be trash.

The Color Management Handbook for Visual Effects Artists by Victor Perez — I do not recommend it.

I read a whole book about this last year and it made me furious. Well, technically the book was about ACES but it was also about HDR and the problems overlap tremendously. I emphatically agree with this entire video and I will be sharing it widely.

> The key is to not become a slave to them. To realize that our worth consists not in our ability to think. And that we are more than that.

I cannot afford to consider whether you are right because I am a slave to capital, and therefore may as well be a slave to capital's LLMs. The same goes for you.

I rest my case — the question concerns a quality, not a quantity. These juvenile comparisons are mere excuses.

If the student could reference notes a fraction of the size of the LLM then I would not be convinced.

Agree. Both sides of the argument are unsatisfying. They seem like quantitative answers to a qualitative question.

It's literally called a "living" wage, and I guarantee you in reality it's nothing more than that, if even. Life tends to always have unexpected costs. I shouldn't need to tell anybody that, including you.

How do you suggest authorities test people for homelessness on public transportation?

Are you proposing any specific laws to manage antisocial behavior?

In the end, I'm certain that the better idea is to simply give people jobs.

> I'm also tired of people becoming parents without considering the financial aspects ahead of time. If you're making minimum wage and are barely surviving, don't have kids until you're on steadier ground.

Young is abolutely the best age to have kids. Ask biology.

If you want a society (I do) then you want a society that supports people having children.

If you want a healthy society (I do) then you want a society that supports people having children at a young age.

Nonsense. You describe a world in which everyone has disposable income to navigate the market, picking and choosing as they please. Capitalism is not that world. Most people are just trying to keep their debt manageable enough to keep a roof over their heads and get to work on time the next day. Get real, guy.

$23.66/hour in Savannah, GA in 2025 is a starvation wage. Savannah has a bad housing squeeze with very few apartments and they still cost nearly $2K/mo when you find them. God bless those poor souls.

That would require everyone having a stable job. Something to think about.

The TCP?

> One caveat: I should be able to use it (and, hence, pay for it) anonymously.

I assume you mean this as a moral claim and I can agree in that case. However, it's meaningless of course and kind of infuriating in any other light, because this is the world everyone has been mindlessly begging for and there is no chance that it comes without extremely severe consequences. An automated world like this means even less power for working people than ever before, so how on Earth do you expect to realize any of these desires? Do you still think capitalists care about your privacy? Even if they did "care" it wouldn't matter because they have to compete.

Nonsense. There is a big difference between the implications of the following claims:

1. The specific people that are currently rich will become richer.

2. The people that are rich at any given instant in the future will be richer than the people that are rich at the current instant.

"The rich are getting richer" almost always means #2, but it depends on the context. #1 may be more interesting to individuals competing for wealth, or for an assessment of individual mobility, but #2 is much more relevant when describing the aggregate conditions of a society. For example, the Gini Coefficient depends on #2, not #1.

I don't think it's a stretch to say it's dishonest to presume the first meaning.

That's what they all say.

If you like the kitchen so much then build one for yourself?