Paul Kinlan published a blog post a couple of days ago [1] with some interesting data, that show output tokens only account for 4% of token usage.

It's a pretty wide-reaching article, so here's the relevant quote (emphasis mine):

> Real-world data from OpenRouter’s programming category shows 93.4% input tokens, 2.5% reasoning tokens, and just 4.0% output tokens. It’s almost entirely input.

[1]: https://aifoc.us/the-token-salary/

This reduces token usage because it asks the model to think in AXON https://colwill.github.io/axon

Yes but with prompt caching decreasing the cost of the input by 90% and with output tokens not being cached and costing more than what do you think that results in?

However output tokens are 5-10 times more expensive. So it ends up a lot more even on price

Even more than that in practice once you factor in prompt caching

My own output token ratio is 2% (50% savings on the expensive tokens, I include thinking in this, which is often more). I have similar tone and output formatting system prompt content.

I've found Neovim to be remarkably stable, even when building from main.

You haven't been using the LSP API then. There have also been multiple breaking changes over the last five years, including breaking compatibility with established default vim keybindings.

A documented breaking change does not mean the application is unstable.

The Neovim developers have been extremely clear that part of the process of getting to 1.0 is finalising the API, and that there will be breaking changes en-route.

I have never experienced this many breaking changes in stable software. There's a reason nvim still hasn't hit 1.0

To be clear, it's fine to have breaking changes. Especially if you're working towards something substantial.

But nvim and its plugin ecosystem seem to be altogether too keen to change absolutely everything and adopt all bleeding edge developments. Even when a mature system would serve the purpose just as well.

Changing default mappings is not a "breaking" change.

It is. And iirc, neovim themselves mark them as such.

I would argue that ambiguity and uncertainty slow down reading, and more importantly comprehension, far more than a few additional characters.

It depends on whom you are optimizing for. Someone who knows the language, but not this system/codebase, or someone who works in this area often?

> I have no intention at all of hosting anything I've made by hand, be it code, photos, recipes, etc.

Do you publish any such items on platforms you don't own (you specifically said you "have no intention of... hosting anything")?

I haven't in a very long time, over a decade at this point.

A few friends and I have a small handful of self-hosted services that we all run on a VPN between our places with stuff like a recipe sharing app, etc., but the number of people with access to that is single digits.

In terms of "hosting anything," I still have my own homelab, and my self-hosting will be limited to this sort of stuff for the foreseeable. A cluster of limited-scope apps that helps me and a handful of friends keep in touch after moving out of our hometown, beyond just chatting in Signal groups.

I won't be putting up my own public website (or portfolio, or whatever; be it hosted on my own infra or not).

Two decades. Rails was released in 2004, IIRC.

I appear to be in the minority here. Perhaps because I've been practicing TDD for decades, this reads like the blog equivalent of "water is wet."

"Welcomes" seems like a stretch.

If you must "choose to enable" encryption, that implies it's off by default. If so, GP's statement is accurate.

No, I mean you must select yes or no. can't use WhatsApp until you make a choice yourself.

Choose to enable backups.

I'm confused. Are you criticising the article, or simply expressing concern for what may happen?

The context suggests the former, but your criticisms bear no relation to the linked content. If anything, your edict to "write tests first" is even more succinctly expressed as "Red/green TDD".

But it is related, isn't it? I wrote "...each swearing they have the secret sauce and the right incantations...". Now compare it to ""Use red/green TDD" is a pleasingly succinct way to get better results out of a coding agent."

Doesn't it sound like the "right incantation"? That's the point of LLMs, they can understand (*) intent. You'd get the same result saying "do tdd" or "do the stuff everyone says they do but they don't, with the failing test first, don't remember the name, but you know what I'm saying innit?"

I'm perhaps uncharitable, and this article just happens to take the collateral damage, but I'm starting to see the same corruption that turned "At regular intervals, the team reflects on how to become more effective" into "Mandatory retro exactly once every fortnight, on a board with precisely three columns".

>Doesn't it sound like the "right incantation"?

It sounds like you have a misunderstanding of what LLMs are/can do.

Imagine that you only get one first interaction with a person that you're having try to build something and you're trying to minimize the amount back and forth.

For humans this can be something like an instruction manual. If you've put together more than a few things you quickly realize that instruction manuals vary highly in quality, some will make your life much easier and other will leave you confused.

Lastly, (human) intent is a social construct. The more closely you're aligned with the entity in question the more it's apt to fully comprehend your intent. This is partially the reason why when you throw a project at workers in your office they tend to get it right, and when you throw it towards the overseas team you'll have to check in a lot more to ensure it's not going off the rails.

I view it as a collection of potentially helpful tips which have worked well for the author, which is exactly how it's presented.

There's no suggestion that this is The Only Blessed Way.

Thank heavens for that separation of powers, otherwise the President would be declaring wars and levying tariffs willy-nilly, without even bothering to check with Congress first.

Presidents have been doing the undeclared war thing since the end of WWII. Nothing new there, the tariffs and other EOs have maybe increased markedly in the last few presidencies.

George W Bush sought and received authorization for Iraq from Congress.

It's not just the war, obviously. This time the President has immunity levels that are unprecedented. And his cronies in Congress and SCOTUS don't seem inclined to rein him in on much.

Americans have forgotten that pieces of paper need to be backed up with threats of violence.

I honestly don't understand US politicians. In my country politicians have egos the size of mountains- they would never let themselves be sidelined.