'Vibe formalizing' is a logical extension of 'vibe engineering' implemented by 'vibe coding'. Sometimes I have trouble with getting the individual puzzle pieces of a problem to fall into place, where a hypothetical 'Move 37 As A Service' to unify informal methods with mathematical rigor deserves to be explored!

Oh dear. Its digital tombstone has been relegated to be adware for crypto gambling.

Before I discovered HN (of which I'm on daily), I was a frequent reader of Groklaw[0]- a site primarily devoted to covering the fragile intersection of the technology sector and legal system; where the two are often at odds with one another. We're more than a decade beyond it's voluntary closure after the Snowden revelations and it's left a large void on substantive coverage of these issues. The site was the blog of an anonymous tech reporter named Pamela Jones that did detailed deep-dives into the parties & issues involved in high-profile lawsuits between tech companies, like Apple vs. Samsung on the issue of design patents for rounded corners, over what have often been patents containing broad language that resulted in hindrances to innovation ranging from being unwilling to license to extortion of revenue streams for entire product lines. Part of why I find the technology industry to be continually interesting is its desire to innovate instead of litigate- there needs to be a check on bad faith actors whose goal is capture of a niche through regulatory means instead of fair competition; else we get these cases relegated to the infamous eastern district of Texas which has historically played favor towards non-practicing patent trolls. I'll be submitting my comment and suggest others do the same.

[0] https://en.wikipedia.org/wiki/Groklaw

On Friday I was converting a constrained solver from python to another language, and ran into some difficulty with subsituting an optimzer that's a few lines of easily written Scipy; but barely being supported in another language. One AI tool found this out and fully re-implemented the solver using a custom linear algebra library it wrote from scratch. But another AI tool was really struggling with getting the right syntax to be compatible with the common existing optimization libaries, and I felt like I was repeatedly putting queries (read: $) into the software equivalent of a slot machine that was constantly apologizing for not giving a testable answer while eating tens of dollars in direct costs waiting for the "jackpot" of working code.

The feedback loop of "maybe the next time it'll be right" turned into a few hundred queries resulting in finding the LLM's attempts were a ~20 node cycle of things it tried and didn't work, and now you're out a couple dollars and hours of engineering time.