The Claude Code leak revealed that Anthropic runs Claude-operated bots on the internet. One should be very cautious in getting swept up in the fund-raising process if they are not seeing first-hand the fruition of all of the flattering claims being presented by strangers on the internet.

" Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".

For each frame our pipeline constructs a scene graph with React then -> layouts elements -> rasterizes them to a 2d screen -> diffs that against the previous screen -> finally uses the diff to generate ANSI sequences to draw

We have a ~16ms frame budget so we have roughly ~5ms to go from the React scene graph to ANSI written. "

I want to get my car's transmission fixed, the mechanic shop is 50 meters away. Would it be better to walk or to drive to a location 50 meters away from my front door?

-

Opus 4.6:

The user is asking whether to walk or drive 50 meters to a mechanic shop, but there's a key nuance here - their transmission needs fixing, so driving might not be wise.

Done

Walk, absolutely. Driving a car with a compromised transmission even 50 meters risks making the problem worse and turning a repair into a more expensive one. Plus, 50 meters is barely a minute on foot.

The practical and opportunistic response is too tell them "Tough cookies" and watch the problems steadily compound into more lucrative revenue opportunities for us. I really have no remorse for these people. Because half of them were explicitly warned against this approach upfront but were psychologically incapable of adjusting expectations or delaying LLM deployment until the technology proved itself. If you've ever had your professional opinion dismissed by the same people regarding you as the SME, you understand my pain.

I suppose I'm just venting now. While we are now extracting money from the dumbassery, the client entitlement and management of their emotions that often comes with putting out these fires never makes for a good time.

There is something about our biology that makes us learn better when we struggle. There are many concepts on this dynamic: generation effect, testing effect, spacing effect, desirable difficulties, productive failure...it all converges on the same phenomenon where the easier it is to learn, the worse we learn.

Take K-12 for instance. As computing technology is further and further integrated into education, cognitive performance decreases in a near-linear relationship. Gen Z is famously the first generation to perform worse in every cognitive measure than previous generations, for as long as we've been recording since the 19th century. An uncomfortable truth emerging from studies on electronics usage in schools is that it isn't just the phones driving this. It's more so the Duolingo effect of software overall emulating the sensation of learning without actually changing the brain state. Because the software that actually challenges you is not as engaging or enjoyable.

How you learn, and your ability to parse, infer, and derive meaning from large bodies of information, is increasingly a differentiator in both the personal and professional worlds. It's even more so the case when many of your peers are now learning through LLM-generated summaries averaging just 300 words, perhaps skimming outputs around 1,000 words in length for "important information". The immediate benefits are obvious, but the cost of outsourcing that cognitive work gets lost in the convenience.

Because remember, this isn't just about your ability to recall specific regex, follow a syntax convention, or how much code you ship in an hour. Your brain needs exercise, and deep learning is one of the most reliable ways to get it. Doubly true if you're not even writing your own class names.

What I am speaking to is not far away or hypothetical, either. Because as of 2023, one in four young adults in the United States is functionally illiterate.

https://www.the74million.org/article/many-young-adults-barel...

https://pbs.twimg.com/media/G-p2hvebQAEkEBg?format=jpg&name=...

Edit: To be clear, I think there are multiple contributing factors. It's just that, in my view, the time/labor shortage is the core of the issue. Everything else feeds into it in some way. The factors eventually start stacking and problems that contribute to the time issue get exacerbated by their own contributing factors.

Economics pressures, for instance. Bad housing economics means couples work maximum hours to afford daily expenses, decreasing available household labor. It also fractures extended family systems when people have to relocate for cheaper housing or better jobs, eliminating the traditional labor-pooling arrangements for childrearing. Generally poor median household economics keep parents in constant anxiety too, which then requires time to be spent on coping routines.

Social atomization has further taken away the kind of pooled childcare labor that used to absorb overflow. Media has displaced churches, bars, parks, and bowling alleys with private screen time, shrinking social circles with scarce opportunities to rebuild them. Car-based infrastructure further reduces local community interaction and subtly dehumanizes neighbors into obstacles who steal parking and slow you down. Remote work and online shopping accelerate this deterioration. The result of all of this? Parents who already don't have extended family, also don't have friends, neighbors. or community to cover childcare needs. The sort of "Hang out at the neighbor's house while I go to my book club meeting." scenario has largely gone extinct because of this.

Even if a couple does better than the average bear in these areas, and they have options, ambient paranoia bottlenecks their outsourcing of childcare anyway. Our media environment has normalized constant fear. Fear that every blade of grass conceals a potential predator, so every adult is regarded as a serious risk to your kid(s). This compounds further because it's gotten to the point where children (and teenagers) can't play outside or otherwise exist independently without supervision. This increases the time parents must spend on daily childcare needs. So not only can they not decrease the time spent, but they now have to spend even more because of it.

On top of all of this, the fraying social fabric creates an effect similar to cellular breakdown. Where those who become disconnected from the larger biological system stop acting for the collective benefit and further prioritize the self, becoming cancerous. This leads to growing numbers of extremist, anti-social individuals with poor mental health. Individuals who both compound the scarcity and isolation of parents, and justify their media-sourced fear of other adults. This is an example of the contributing factors to the contributing factors.

You get the idea.

The below captures this perfectly. The author is trying to explain that vibe-coding their own frameworks lets them actually "understand" the code, while not noticing that the LLM-generated text they used to make this point is talking about cutting and sewing bricks.

> But I can do all of this with the experience on my back of having laid the bricks, spread the mortar, cut and sewn for twenty years. If I don’t like something, I can go in, understand it and fix it as I please, instructing once and for all my setup to do what I want next time.

I'm not sure if this was intended or not, but this is a common NIMBY refrain. The argument of "This thing being advocated for that I'm fighting against isn't something people want anyway". And like walkable neighborhood architecture, extremely few Americans have access to light rail. Let alone light rail that doesn't have to yield to car traffic.

Regardless, the cost arguments fall apart once you take the total cost society pays for each system instead of only what the government pays. Because when you get the sum of road construction & maintenance, car acquisition, car maintenance, insurance, and parking, it dwarfs the cost of the local transit system. Break it down on a per-consumer basis and it gets even uglier. New York City is a good example to dive into, especially since it's the typical punching bag for "out-of-control" budgets.

Quick napkin math pins the annual MTA cost at $32-$33 billion and the total cost of the car system between $25 and $44 billion per year. Since the former serves somewhere around 5.5 million riders, and the latter only about 2 million, the MTA costs $5,300-6,600 per user annually where the car system costs $12,000–$22,500 per user annually.

I wish I remembered the exact versions involved. I mostly just recall how pissed I was that it was fighting me on changing a single line in my go.mod.

So, essentially, Minnesotans are being asked to subsidize facilities that will employ only a handful of specialists, raise electric bills, strain water resources, produce outputs many residents actively oppose, and accelerate the automation of their jobs...all while the state offers ~$500 million in support to these companies and nothing to offset the costs borne by residents.

My personal opinion is that while smut won't hurt anyone in of itself, LLM smut will have weird and generally negative consequences. As it will be crafted specifically for you on top of the intermittent reinforcement component of LLM generation.

If I program a machine and it goes out into the world and hurts someone who did not voluntarily release my liability, that's on me.