Bend programming language

“This is a vibecoded project, not a resource for learning modeling for formal verification.”

“the laws are formally verified, as in Lean or Rocq (but much faster)”

“I hope people will give it a second look, and not just stop at this post which is a gross misrepresentation of Victor Taelin's work.”

“bend is just one example of people having ai build things for them they don't understand”

“isn't some vibe-coded fantasy, and the author has been working on this stuff for a loooong time”

“it had only 24-bit integers, a 2 GB memory cap, and other limitations that made it unpractical”

“The whole thing smells like somebody trying to pull an LLM-fueled Sokal Hoax on the programming world.”

“it's obvious that the translation from business requirement to proof target still requires coding and can contain bugs”

“this whole bend thing might be an exact fit for the problem space”

“It would work much better if a) tokens were free and b) computation, therefore retries, didn't take any time at all.”

“Having a checker that is just fast by construction, regardless of caching, was a top design priority”

“They just recycled the Bend1 repo for Bend2 even though it's a completely different language.”

“Every single part of Bend is an intentional choice I made after considering every alternative.”

“despite the presentation of their work, which has some obvious flaws”

“there's no such thing as a computer programming method or discipline that "blocks AI mistakes via proof."”

“Cool project! This is really interesting”

“Seems like a big limitations. But I guess that's what lets it run without GC, on GPUs, etc.”

“I'm only reading these comments because i liked the interaction combinator Bend language.”

“Pivots are cool but why reuse the name and cause confusion?”

“has no auditable history, reproducible builds, artifacts/releases, force pushes and breaks literally EVERY fork/PR”

“Thank you for adding a 5-line AGENTS.md. Other projects force you to install skills or MCP even when they're just doing the same thing.”

“Glad to see a new release of Bend, fascinating cutting-edge stuff.”

“I'm not sure what its proving other than there will be cases that proofs can't help you with.”

“A complete implementation have been released”

“Bend would make Dijkstra happy even when proof checking can't verify if the laws are what was actually meant.”

“Since AI is going to be here anyway, why not make it safer and more useful?”

“it editorializes and oversells. It presents the claims of the work as an all encompassing solution”

“You're basically shrinking the state space of what is considered a "correct" program per your spec.”

“a variation of programming language like this is bound to win”

“LAWS.bend makes you need to read astronomically less code”

“It basically succeeded but Claude (Opus 5) did have some complaints”

“That's a destruction of trust, which is kinda important if you want people to build on your language.”

“From what I can tell it looks nice. I like the syntax.”

“I like the idea of a language intended from the start to be proved and it seems very compelling given coding agents.”

“they just modify the law itself to fit the new feature they are working on, which defeats the point”

“I argue this is the right tradeoff, because AI write proofs, and AI time is cheap, while bugs take human time, which is expensive.”

“it is not a pretty file and it has a lot of gambiarra and AI slop for now”

“Cool to see Bend 2.0 release!”

“I was annoyed with ads and limitations so I built one for myself.”

“Programs that can be easily expressed in Bend will benefit greatly from HVM.”