If it's so easy to containerize these things then why aren't more devs doing it and these stories going away? I for one am actively avoiding the agentic coding switch because I have no interest in opening my home environment to a remote corporate LLM just to write code faster. But of course I'm missing out, as soon as I have more than one source file that I want my chat LLM to analyze in a single go.

Leaning on overworked metaphors ("load-bearing"), overly-declarative/posturing constructions ("it's not this, it's that"), barefaced sales-y smarm ("you're not wrong!") is the kind of language that takes over the higher up the management inverted-ice-cream-cone you go.

Always the smarmy tone.

I find it a little puzzling when a language ships the one build system to rule them all. I get that it saves some decision stress but it also is a monoculture. Gradle vs Maven in Java at least puts competitive pressure on each; c/c++ obviously have many options; even Haskell had/has stack vs cabal.

Having said that, given sqlite's tiny type universe I can't imagine TC would be at all slow.

Two showstopper problems with this:

1. Many of "us" don't like interacting with LLMs more than we have to, and view reading as a pleasure that would be extinguished instantly at a chat prompt.

2. It lazily implies that the essence of an article is so easy to communicate that it can be compressed into a prompt. There's a reason for titles, subtitles, open sentences, hero images, paragraph openers, etc etc: they pull you in, establish tone and voice and so forth. Where are the prompts that can entice a reader to even skim it much less plug into their favorite chatbot?

Point being, ymmv.

> The founder has it all figured out: the problem was never the plan. The problem was the execution

"Execution" being one of those magic business words, I've said this exact thing but only once lampooned thusly did it dawn on me how psychotic it is. If VC-funded startups are almost by definition about "a big vision", then the vision is never wrong -- a self-consuming logic answered by the magic of Execution.

Interestingly, what is ignored there is the founder is also the CEO here, so if the execution was bad ... shouldn't he be fired?

https://www.zdnet.com/article/linus-torvalds-talks-ai-rust-a...

US apparently still has a functioning democracy, at least when candidates ignore the consultants and insiders and speak straight to the voters. Worked for Trump after all, remember that in 2016 the establishment was against him. Sure he's rich but that's not why he "won" (popular vote aside :( )

Just like Maga/populist right, the left can beat the billionaires if they're willing to take the message to the people.

I'm not even sure losing this method is such a bad thing. Tooling, build scripts, home networking -- any learning you gain from stumbling through man pages and trial-and-error at best results in some hard-won, single-purpose scripts, the knowledge will evaporate instantly b/c everything is so bespoke, "fix once and forget" until you have new gear and have to solve new problems years later.

Presenting a well-specified problem thoroughly to an LLM, then analyzing results and testing the output, is valid problem solving.

When you see fintech companies talking up the virtue of "looping" stablecoins, or pushing wobbly derivatives like the spaceX synthetics, it's hard to see anything good coming from the integration of "crypto rails".