Bet you didn't come up with that comment by first discarding a bunch of unsuitable comments.

I hired an artist for an oil painting.

The artist drew 10 pencil sketches and said "hmm I think this one works the best" and finished the painting based on it.

I said he didn't one shot it and therefore he has no ability to paint, and refused to pay him.

You learned what was unsuitable over your entire life until now by making countless mistakes in human interaction.

A basic AI chat response also doesn't first discard all other possible responses.

How often do you self edit before submitting?

because commenting is easy and solving hard problems is hard

My experience of the book was similar: the first third was great. Great idea, brilliantly executed. Definitely worth it for the first third alone.

In a way, maybe it going off-piste is coherent with the idea of the first third. I'm sure this was not the author's intent, but fun from an ironic perspective.

It certainly invites that level of meta-commentary on its own structure, though I agree it's inadvertent. And I know at some point someone is going invoke that point in full sincerity as if its an answer, and whatever that is, the satisfied meta-commentary that makes too much of irony as if its a sincere insight, I feel like is just looming as a possible and frustratingly shallow justification of the book. There's an interesting question there of the scales of abstraction at which anti-memes could function, and that's fascinating but as you noted in this instance not necessarily intentional.

It makes me think of the movie Doubt, where I remember being sincerely confused as to the central accusation at the center of the movie (though retrospectively its obvious and I knew it was at least one possibility but I wasn't sure if there was perhaps a different interpretation), and was told that not being sure was the point and by expecting an answer I was missing the point since the whole movie is about "doubt". I felt this explanation was, frankly, just stupid. Just because you're going meta doesn't mean any point coherently registered in the form of meta-analysis is insightful. But anyway, I'm off the rails a bit now going after imaginary adversaries, but agree with everything you've said.

That was very well articulated. I'm going to hold on to your point about trivial meta-analyses masquerading as serious ones, sadly a very common type of gotcha in tech-aligned circles.

Thanks! I was mostly building off of your point I think. You have to imagine there's a short term or phrase for this. The overestimation of the value of going meta, or treating the move of going meta like it's a skeleton key when it's actually frivolous.

>> you will not have that delightful experience of encountering something unexpected along the way to filling it.

> There's nothing stopping you from doing that with an LLM.

There may be, though. The LLM's initial output may anchor your thinking in insidious ways that may not be obvious at all especially since you're feeling productive. I bet the lack of confidence around starting would also increase over time every time you use an LLM to get over the hump.

Not so far.

I'm not talking about using a default mode LLM with LinkedIn Standard Obsequious Bullshit as a conversational imperative that emerges from simple prompts interacting with the heaviest weights. It pushes back because I told it to and it has redirects around common LLM failure modes, and modes unique to how I use them. That's in a set of instructions I've had a bunch of different models tear apart so I could put it back together better.

I treat it and describe it as a language coprocessor, not a buddy. The instructions are the kernel I boot it with.

Yeah, precisely. My "Bobby" knows my voice, but is not me, and is bad at using it. It is aware of all the tropes, and I've built a writing skill that describes, in great detail, how I write. I have also set it up to challenge me, not make me feel good.

Moreover, it's not like I spend my entire writing time arguing with an LLM, lol. I spend more time writing myself and/or doing research on the internet without an LLM, because sometimes they still get things wrong.

In short: it's a tool, not a solution.

My experience is the same. There are modest gains compensating for lack of good documentation and the like, but the human bottlenecks in the process aren't useless bureaucracy. Whether or not a feature or a particular UX implementation of it makes sense, these things can't be skipped, sped up or handed off to any AI.

What are these bottlenecks specifically that you feel are essential?

Am trying to compare this to reports that people are not reviewing code any more.

When features and their exact UI implementations are being developed, feedback and discussions around those things.

> There are many reasons for the lag in productivity gain but it certainly will come.

Predictions without a deadline are unfalsifiable.

Well the thing with predictions is that they are in genral difficult - esp. when it comes to those in future :-D

Are we just assuming nobody is programming commando anymore?

If you don't want to or can't install a Sustainiac pickup, you can get a much cheaper handheld one-string "E-Bow" that does the same thing. It's not as easy to use as a Sustainiac and you can't also be playing with the whammy bar unlike with a Sustainiac, but you can get it to do tricks a Sustainiac can't do: see the "spiccato" section in https://www.youtube.com/watch?v=b0V3pzxma-8

I've also managed to make an E-Bow work with a steel-string acoustic guitar (but only on one string IIRC).

Happy for you, but GitHub has plenty of webcam feed URLs, webcam viewers, Roku code etc. You "built" it for some value of 'building' but it certainly doesn't seem the same kind of 'building' as described in the first three sentences of your post.

It's nice you got something out of it in just two hours. If the LLM companies are doing their caching right, the next person to ask for this set of apps with prompts close enough to yours can get it in five minutes.

Also there's a typo in the URL.

The inching-towards-acceptance of crappy processes is quite influencer-driven as well, with said influencers if not directly incentivised by LLM providers, then at least indirectly incentivised by the popularity of outrageous exhortations.

There's definitely a chunk of the developer population that's not going to trade the high-craft aspects of the process for output-goes-brrr. A Faustian bargain if ever I saw one. If some are satisfied by what comes down to vibe-testing and vibe-testing, I guess we wish them well from afar.

This is the chapter title for a sort-of book I'm working on, and it's the central philosophy I'm building the book around.

I'm not going to change a good chapter title (and I do think it's a good chapter title) just because people on Hacker News won't read a few paragraphs of content.

A dishonest title would be "Code is cheap now" or "Programming is cheap now". I picked "Writing code is cheap now" to capture that specifically the bit where you type code into a computer is the thing that's cheap.