Also worth pointing out that the N isn't too terribly large: the article says that the ecosystem has about 4000 plugins and themes? With that volume, you could almost reasonably just use static analysis to flag suspicious plugins (saving tokens), have an AI do a pre-analysis and pass to a human for final decision-making.

The entire thing is actually kind of irritating to me, because it's kind of an insult to small farmers- an influential techie comes in and generates all kinds of hype about an AI running a farm, sets the project up as if it's going to be this revolutionary experiment, then apparently completely forgets about it the next time something new and shiny pops up. Meanwhile the project completely fails to fulfill the hype.

Not to mention, I feel a little bad for the agent- admittedly in the same way I'd feel "bad" for a robot repeatedly bumping into a wall. I wish he'd shut it all down, honestly.

> String Slicing > You can extract a substring using bracket syntax with a range: s[start:end]. Both start and end are byte offsets. The slice includes start and excludes end.

Given that all strings are UTF-8, I note that there's not a great way to iterate over strings by _code point_. Using byte offsets is certainly more performant, but I could see this being a common request if you're expecting a lot of string manipulation to happen in these programs.

Other than that, this looks pretty cool. Unlike other commenters, I kinda like the lack of operator precedence. I wouldn't be surprised if it turns out to be not a huge problem, since LLMs generating code with this language would be pattern-matching on existing code, which will always have explicit parentheses.

And yet, it's still somewhat better than the Hacker News comment using bastardized English words.

Ultimately, it's the same way you ship human-generated code at scale without causing catastrophic failure: by only investing trust in critical systems to people who are trustworthy and have skin in the game.

There are two possibilities right now: either AI continues to get better, to the point where AI tools become so capable that completely non-technical stakeholders can trust them with truly business-critical decision making, or the industry develops a full understanding of their capabilities and is able to dial in a correct amount of responsibility to engineers (accounting for whatever additional capability AI can provide). Personally, I think (hope?) we're going to land in the latter situation, where individual engineers can comfortably ship and maintain about as much as an entire team could in years past.

As you said, part of the difficulty is years of technical debt and bureaucracy. At larger companies, there is a *lot* of knowledge about how and why things work that doesn't get explicitly encoded anywhere. There could be a service processing batch jobs against a database whose URL is only accessible via service discovery, and the service's runtime config lives in a database somewhere, and the only person who knows about it left the company five years ago, and their former manager knows about it but transferred to a different team in the meantime, but if it falls over, it's going to cause a high-severity issue affecting seven teams, and the new manager barely knows it exists. This is a contrived example, but it goes to what you're saying: just being able to write code faster doesn't solve these kinds of problems.

By contrast, the colloquial use feels like an abbreviation of the implicit phrase "it begs for the question to be asked", which makes so much more sense than the "correct" meaning that if I'm being perfectly honest, I'd rather use it.

I like Wikipedia's alternate name for the fallacy: "assuming the conclusion", because it explains what's actually happening.

"Curmudgeon" itself is interesting, because while it's not particularly common, I actually think a lot of native English speakers would recognize it because it's got a lot of character- for some reason, the way it feels to say and the way it sounds almost has some of the character of the meaning.

> Earlier this year, we added preset options to tailor the tone of how ChatGPT responds. Today, we’re refining those options to better reflect the most common ways people use ChatGPT. Default, Friendly (formerly Listener), and Efficient (formerly Robot) remain (with updates), and we’re adding Professional, Candid, and Quirky. [...] The original Cynical (formerly Cynic) and Nerdy (formerly Nerd) options we introduced earlier this year will remain available unchanged under the same dropdown in personalization settings.

as well as:

> Additionally, the updated GPT‑5.1 models are also better at adhering to custom instructions, giving you even more precise control over tone and behavior.

So perhaps it'd be worth giving that a shot?

> Billions of dollars are spent — and largely wasted — every year on professional development for teachers that is curriculum-agnostic, i.e., aimed at generic, disembodied teaching skills without reference to any specific curriculum.

> “A huge industry is invested in these workshops and trainings,” argued a scathing 2020 article by David Steiner, executive director of the Johns Hopkins Institute for Education Policy. “Given, on average, barely more than a single day of professional support to learn about the new materials; knowing that their students will face assessments that lack any integration with their curriculum; and subject to principals’ evaluations that don’t assess curriculum use, teachers across America are barely using these new shiny objects — old habits win out.”

> Mississippi improved its training through a 2013 law mandating that elementary school teachers receive instruction in the science of reading. It also sent coaches directly into low-performing classrooms to guide teachers on how to use material.

> Note: This step will become much easier and concise when the sibling-index() and sibling-count() functions gain support (and they’re really neat). I’m hardcoding the indexes with inline CSS variables in the meantime.

The inline links there go to https://css-tricks.com/almanac/functions/s/sibling-index/, which is pretty nifty honestly.

There are also runtimes like e.g. Hermes (used primarily by React Native), there's support for separating operations between the graphics thread and other threads.

All that being said, I won't dispute OP's point about "handling concurrency [...] within the language"- multithreading and concurrency are baked into the Golang language in a more fundamental way than Javascript. But it's certainly worth pointing out that at least several of the major runtimes are capable of multithreading, out of the box.

To put the same thing another way- whether or not you or I *think* LLMs can experience feelings isn't the important question here. The question is whether, when Joe User sets out to force a system to generate distress-like responses, what effect does it ultimately have on Joe User? Personally, I think it allows Joe User to reinforce an asocial pattern of behavior and I wouldn't want my system used that way, at all. (Not to mention the potential legal liability, if Joe User goes out and acts like that in the real world.)

With that in mind, giving the system a way to autonomously end a session when it's beginning to generate distress-like responses absolutely seems reasonable to me.

And like, here's the thing: I don't think I have the right to say what people should or shouldn't do if they self-host an LLM or build their own services around one (although I would find it extremely distasteful and frankly alarming). But I wouldn't want it happening on my own.

This just reminded me of AngeTheGreat's incredible video series showing his engine simulator- absolutely worth checking out, considering it's optimized enough to run in real-time! The fact that he's simulating it well enough to generate realistic sound is absolutely mind-blowing.

https://www.youtube.com/watch?v=RKT-sKtR970

To make matters even more complicated, when I do use my first name, I almost always use an abbreviation. The only people that use my full first name are my parents, sister, and (occasionally) my wife, and it's really off-putting to hear it otherwise.

Names are interesting and weird.

1: https://tvtropes.org/pmwiki/pmwiki.php/Main/TheHerosJourney 2: https://tvtropes.org/pmwiki/pmwiki.php/Main/Kishotenketsu

I'm not sure what point you're trying to make here? That specific transition vector would be one such vector among several in a given ruleset. You're correct that for any ruleset, if I don't have at least one vector that can get me away from the origin, I'm stuck there, but then I also have to consider that I still might not be able to get to where I want to go. If I have the ruleset [(2, 0), (-4, 2)] I still can't get to (3, 5).