I don't judge content for being AI written, I judge it for the content itself (just like with code).

However I do find the standard out-of-the-box style very grating. Call it faux-chummy linkedin corporate workslop style.

Why don't people give the llm a steer on style? Either based on your personal style or at least on a writer whose style you admire. That should be easier.

Because they think this is good writing. You can’t correct what you don’t have taste for. Most software engineers think that reading books means reading NYT non-fiction bestsellers.

While I agree with:

> Because they think this is good writing. You can’t correct what you don’t have taste for.

I have to disagree about:

> Most software engineers think that reading books means reading NYT non-fiction bestsellers.

There's a lot of scifi and fantasy in nerd circles, too. Douglas Adams, Terry Pratchett, Vernor Vinge, Charlie Stross, Iain M Banks, Arthur C Clarke, and so on.

But simply enjoying good writing is not enough to fully get what makes writing good. Even writing is not itself enough to get such a taste: thinking of Arthur C Clarke, I've just finished 3001, and at the end Clarke gives thanks to his editors, noting his own experience as an editor meant he held a higher regard for editors than many writers seemed to. Stross has, likewise, blogged about how writing a manuscript is only the first half of writing a book, because then you need to edit the thing.

My flow is to craft the content of the article in LLM speak, and then add to context a few of my human-written blog posts, and ask it to match my writing style. Made it to #1 on HN without a single callout for “LLM speak”!

So are we basically saying that LLMs work most effectively on codebases that exhibit good quality coding practices, but are not themselves particularly good at creating such quality code themselves, since they were trained on all the code that exists.

I don't know what conclusion to draw from that. Maybe that there's no such thing as a free lunch, after all.

The conclusion I draw is that LLMs need a human expert with some taste and agency to empower/supervise them. Just like human dev teams do.

This is a deranged take. Lots of slurs end in "er" because they describe someone who does something - for example, a wanker, one who wanks. Or a tosser, one who tosses. Or a clanker, one who clanks.

The fact that the N word doesn't even follow this pattern tells you it's a totally unrelated slur.

It's less of a deranged take when you have the additional context of a bunch of people on tiktok/etc promoting this slur by acting out 1950s themes skits where they kick "clankers" out of their dinner or similar obvious allusions to traditional racism.

Anyway, it's not really a big deal. Sacred cows are and should always be permissible to joke about.

I drive a 2022 EV which has physical buttons for all the things you mention so you're good for a while

All I can suggest is that you watch some of Adam Curtis's work.

I for one am quite happy to outsource this kind of simply memorisation to a machine. Maybe it's the thin end of the slippery slope? It doesn't FEEL like it is but...

Why even learn how to read when you can just yell at the computers?

Isn't this just a rhetorical trick where by referring to a particular technology of the past which exploded rapidly into dominance you make that path seem inevitable?

Probably some tech does achieve ubiquity and dominance and some does not and it's extremely difficult to say in advance which is which?

As a pessimist who's often right, and not rich, this resonates.

But how can this be true? Surely you get rich by being right?

Pessimists think nothing is worth doing, and are frequently right. But they will never catch the occasional thing that is worth doing. Some of the optimists will.

But optimism favors action, while pessimism favors inaction. And action vastly (and compoundingly) increases the amount of opportunities for being right.

Pessimists are just as often wrong too! Clearly the person you're replying to is an "optimist". :)

To be clear, I don't think there's a strong correlation between being rich and being a pessimist/optimist.

And to your original point, being right cannot possibly be biased towards optimism or pessimism. Any apparent correlation is more of a reflection on what everyone else thinks... and they are wrong! Cheers to being right!

Agreed, optimism/pessimism is just about our disposition to the world as we perceive it (ie. glass half full or half empty). It is orthogonal to understanding and prediction. A perfect Buddhist is neither an optimist or pessimist but can still be better or worse at predicting the future.

I do think pessimists, especially of the depressive variety generally do not get rich. The reason is that getting rich is hard, everyone nominally wants it, so it’s highly competitive and there are no easy paths. To find a path generally you have to take an action that almost by definition is low probability of success. You don’t have to be a beaming cheerleader to make this happen, but being an eyore is most likely disqualifying.

I remember reading that slightly depressed people tend to have a more accurate world view.

Perhaps there is something to the saying ignorance is bliss.

I might be misunderstanding, but I wouldn't call "un-depressed" people ignorant.

I also think depressed people would regress to the average if they weren't depressed. It's not a sustainable way to think harder and open your eyes to the world around you.

Yes I remember reading that too and it resonated. As a slightly depressed person I can't believe the delusionally positive spin people seem to put on everything and nonetheless this seems to be a winning strategy for them. I never could explain that.

Starting with an accurate world model, no matter how dispiriting, seems to be a prerequisite for knowing the most effective action to take.

Please share, I've been looking for such a chair for so long!

These things are incredibly subjective/personal, but for me the chair was a Stressless View (large size). It was not cheap.

Varier Gravity might be up your alley

This is completely true. I've spent decades, ie my whole adulthood, looking unsuccessfully for a properly comfortable reading chair.

My perfect reading chair: the "Skye" model designed by Tord Bjorklund for Ikea in the 1970s. Its shape is essentially like an Adirondack chair connected to an ottoman, but padded and leather covered. Insanely comfy and perfect for reading.

Similar but more famous is the LC4 Chaise Longue designed by Le Corbusier.

Looks nice to lounge in but to read a book one needs arm rests, surely?