adamtaylor_13

"There is way that seems right to a man, but the end thereof is death." Proverbs 14:12

By my own admission, I often place importance on the wrong things. I am building the discipline of putting the truly important things first.

Is this a comment toward the author?

Surely the irony isn't lost upon you that they literally are advocating for getting a life.

I think it boils down to most of these folks don't have anything better to do. Or worse (the bucket I find myself in) this type of work is the most mentally stimulating thing I have, so I do it willfully at the expense of my wife and cats.

I'm still building the discipline to put the important stuff first!

I think part of the lie is that we live for and unto ourselves. We instinctively know it's not true, yet for much of our lives we live as if it is. Until one day we find out what we knew all along.

When you suddenly become unable to "give anything" to others and become the one who must be given to, you feel a disconcerting sense of loss and powerlessness.

I don't think it really has anything to do with capitalism.

I may be crucified for asking this but: is there any proof that slop matters beyond our sensibilities as developers?

If the code is ugly, but defects are low—does it matter?

If the code is hard to read, but clients are happy—should I care?

Genuinely asking. Weird times we live in.

Or tell me what it explicitly doesn't do. I like marketing that says, "We don't X"

It's very clear and not "clever"

Ours is a religion of submission to God, literally calling upon us to "pick up your cross daily." Which is, to die to yourself in submitting to God's will.

Various books of the Bible were written to very specific peoples at specific times, but at the same time, to all Christians everywhere. It takes wisdom to discern to which group does an instruction apply, and when?

This isn't to say that under no circumstances can you break the law; consider Christians in countries where Christianity is unlawful, they consistently break the law and defy the government because submission to God supersedes submission to government.

This passage specifically establishes that building a "Christian Caliphate" is not a goal of Christianity nor should it be a goal of any individual Christian. In general, the government is an institution put in place by God. The general principle is that God is sovereign, so by resorting to violence to assert yourself and your rights you are in no small way asserting your own will over His.

Books have been written on this, so I'll stop here. If you're interested, you can to much deeper on this.

I just wanted to clarify the drive-by theology indicating Christians are somehow "siding" with the "elite" is a very poor understanding of the scripture and ignores basically all of history.

If I recall correctly that was a bug, not malicious intent. Hanlon's razor makes me presume that's likely.

I love AI. I'm just as AI-pilled as the next guy.

But, somewhat ironically, LLMs are unbelievably bad at writing.

I can read thousands of words from my favorite authors without getting annoyed by their tics and their grammar. People like Nikhil Suresh literally make me laugh out loud when I read their writing. But something about AI-slop-prose is just obvious and gross and annoying to read.

This article wasn't written for folks who just want to "turn it off". If that's you, by all means do so.

New people coming into the field will likely not have the privilege of deciding how much/little to use AI, just like I didn't really get a choice about whether I wanted to use CI or wanted to SSH straight into prod to deploy. As the industry changes, you change with it if you like being a hire-able professional.

This article was written for the folks that are interested in using AI while shaving off some of the sharper corners.

It is unfortunately wasted on people who believe you can just stuff cats back into bags.

Btw Fable beat Pokémon with just vision.

I asked Opus 4.8 to help me design an adapter for a 3d printed part and it actually modeled and GAVE ME the part.

That blew my mind. It doesn't surprise me that Opus 5 ups the ante.

> shares game design field manual written entirely by AI

I fixed the title for you.

You can opt out of training.

If you don't believe checking the opt-out box actually opts you out, then this sentence could be said about literally any provider.

This is part of why I switched to Grok 4.5

I don't need more powerful models, I need one that responds fast enough that my attention doesn't wander to other tasks. Grok 4.5 is so fast I can just use it in-band without swapping to other tasks.

Slower than Opus 4.8, which was already miserably slow, is indeed a step in the wrong direction.

I never see emdashes squeezed tightly to the word before them.

I only ever see them with an AP-style spacing before and after.

This has been my experience as well. While not a full "factory", I've got several mature vibed software projects.

More often than not you can "feel" when the quality has degraded. Many of these pieces leave you hanging on the assumption that once it's slopped up that's the game, it's over, you're cooked, straight to jail.

But I've yet to reach that position and be unable to pop the hood, identify the issue, and agentic-ly clean it up.

The post explicitly says it's not a skill issue, but I've yet to see any situation where an average engineer can't unslop their codebase.

On a related note, I was just noting to my co-founder, as we struggle to write good case studies for our website, that I find LLMs are astoundingly bad at writing good prose.

We all know the "AI-tics" that give away a sloppily AI-written piece, but even if you steer them, they still struggle to write consistently high-quality prose.

Somehow I feel that the work of a good copywriter has never been more noticeable.

Is a company ever really just "ticking along" though? Seems to me like you're always sliding one way or the other, largely due to leadership at the top.

I don't understand how this will interact with llms.txt files (or if it does/will)

Ideally AI should scrape 400 different competing websites, those that have well-designed llms.txt files based on my query should rise towards the top, no?

I understand this is incredibly oversimplified but something like that should be the goal.

I disagree with your assertion that Trump is somehow committing genocide against Palestinians while also acknowledging that the situation there is awful and I pray it ends soon.

But last I checked the Israeli-Palestinian conflict is a few thousand years older than our sitting president.

Wouldn't that be in the authors' interest to disclose, if true?

I think you're 100% correct that you need to feel the pain that the agent is supposed to solve. It's like trying to explain to a junior the power of Rails if they've never even built a regular static HTML website. It's going to be very difficult for them to understand why things are the way they are.

I'm very allergic to "solutions just because we can". In fact, one way I use AI that may be slightly not-mainstream is that I use AI to actively pursue subtraction that I couldn't otherwise do: cutting down on all my tools I've built over the years, culling cruft: notes, scripts, comments, etc. until I'm left with a smaller footprint of stuff I know is useful.

Actually I feel like I'm in the goldilocks zone right now. I've tried automating more for the sake of automation, and didn't really feel any more productive. My workflows have grown naturally as I feel like AI can fill certain gaps, and as I watch other people use AI successfully.

Right, but the original commenter said "living out his genocidal fantasies", which means he is actively performing genocide on someone and it also implies this is something being done with active, excitement.

I'm simply asking who are these people being genocided?

Genuinely curious, who is Donald Trump genociding? Or am I misunderstanding what you mean by "genocidal fantasies"?

I don't have the energy to cynically squint at everything in my life. If a company says "We won't track you" I'll believe it until proven otherwise.

When these companies prove dishonest, I'll adopt skepticism.

I wanted to document this largely for myself (and because other folks have asked me this question), so I ended up writing a blog post on it: https://adamtaylor.me/posts/how-i-use-ai

I hope that doesn't run afoul of self-promotion rules. I just thought it'd be nice to have this answer somewhere it can evolve over time.

It's a flippant answer to a real question. Anthropic, OpenAI, and even Grok have "Don't train on my data" knobs.

Whether you trust them is different, but there ARE knobs on other hosted AI companies.

If rural America is that unappetizing, you understand you can just go live somewhere else, right? There is a very deep-seated hatred here that I suspect has little to do with actual "rural people".

America is what it is. The only thing that will change it is leaning in not bemoaning "rural people" on Hacker News.