Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- My main experience with the demo on the site is that I asked it to add a simple feature which would not even necessarily let you win the game, and it would spend >100k tokens in a loop of "laws broken" until maybe adding it, maybe not. After burning half a million tokens just to add an extra line of walls so that teleporting 2 squares up wouldn't let me win, my API key got rate limited and broke the loop.
On top of that, the solutions feel like patchwork. I asked it to let spacebar flip the board horizontally, and it responded by making the board completely symmetrical including 2 flag poles. At some point it just has to say "this isn't possible without breaking the laws" or think of an actual workaround, because if I was making a game, suddenly having 2 finishes would be unwanted behavior for me.
by djaro - > LAWS.bend
I like the law idea, but what i found they end up doing is they just modify the law itself to fit the new feature they are working on, which defeats the point.
Which means some laws needs to be frozen. But not all laws, otherwise you can't add or modify anything. So the judgement is still on the human part, and we're back to meatbags being the bottleneck.
I've seen some success adding these proof-like checks to CI every time agents do something irrational. I definitely think it should be part of every codebase.
There's also https://code-contracts.cc/ which co-locates code and proofs together.
by RomanKornev - Cool idea. I tried using it to port a little meeting fixer cron job I vibe coded, it seemed a natural fit as its essentially trying to satisfy invariants in my calendar.
It basically succeeded but Claude (Opus 5) did have some complaints:
'Base ships one arithmetic law, U32.add_comm. There is no order theory. About 60 of PROOF.bend's 163 lines are cmp_refl, and_false, and_comm, le_max_l, le_max_r, add_succ — facts you'd assume exist. You'd write them once per project and never again, but budget for them.'
'Base's Nat.max is unusable in a proof. It's Bool.pick(Nat, Nat.is_lt(a,b), b, a), and a proof can't case on a computed value. I wrote a structurally recursive nat_max so it unfolds in lockstep with Nat.cmp.'
'The law I most wanted: "no two output plans overlap." I didn't state it. It needs the sortedness of collapse's input as a hypothesis, and Base's List.sort ships no sortedness law — so getting there means proving merge sort correct first. That's the honest measure of the gap between "provable in principle" and "provable this afternoon."'
I've got basically a minor in CS so I'm a dummy when it comes to proofs. I don't know if this is valuable feedback or simply Claude misunderstanding something.
by svachalek - > In the post-AGI economy, humans will eventually stop writing and reading code, but we still need an ambiguity-free way to tell the AIs building the world around us what we want done.
> With laws, our intents can be much more precise than natural language.
Doesn't this just mean that the code is now "laws", ie. the code is now the spec.
Given this, is there any reason think that writing the "laws" for a complex system is any easier than writing the old-fashioned code that implements it?
by runeks - Gotta say, having followed Taelin on this project since mid 2023, this was not the response I expected when this language first dropped.
It's interesting how cosmetics drive discussion, and how HN comments are weirdly divided in a very dismissive or skeptical camp and those acting incredulous and offended at the reaction of the former.
What I expected instead was a lot more discussion about use cases, benchmarking, possibilities, limitations (that aren't about git history) and the scope of future development.
by meghanto - This project's repo has 20K stars with only 500 forks, with less than 300 issues(including closed). Something's not right.
Compared to other programming languages:
- Gleam: 22K stars, 1K forks, 3K issues
- V: 38K stars, 2.3K forks, 11K issues
- Ruby: 23K stars, 5.6 forks, 19K issues
- Zig: 43K stars, 3K forks, 14K issues
It got 16K stars just in 4 months too. https://www.star-history.com/?repos=bendlang%2Fbend
Also how would anyone trust this? I've never seen a programming language that doesn't have 1) changelogs 2) way to download older versions 3) commit history.
I don't understand why the author thought deleting the commit history was a good idea. Imagine seeing this project for the first time. It's a repo with 20K stars, but no commits, and suspiciously few issues and PRs. It doesn't look legitimate.
---
I'm not familiar with academic procedures, but a pdf on a repo, written by Fable and has no reviews, doesn't seem like a proper 'paper' to me.
by plastic041 - My read on this, after ingesting a good amount of content on the history, is:
- this Bend is not really related to the old Bend (only in name)
- this Bend doesn't really have anything to do with interaction combinators
- this Bend is a QTT, with a change to affinity which enforces a good performance property for GPUs
- the "higher order at comptime" is neat, reminds me of Andras Kovacs' work on 2ltt and staging in dependently typed languages.
- this Bend is likely to be good at "balanced recursive computations on ADT", and can parallelize them ... but won't be as good as CUDA or e.g. Futhark on dense rectangular array computations
- performance needs improvement in the scheduler, to possibly help with balanced work (looking at the n queens and symbolic regression numbers)?
How are you going to handle search or synthesis over irregular structures (SupaGen)?
by mccoyb - Hi, I'm the author.
HN staff: someone posted before me. Could we change the title to "Bend - a language that blocks AI mistakes via proof and runs on GPUs"?
Everyone: feel free to ask any question, but I'd be highly appreciative if you could be a bit civilized and respectful this time. I've worked on this for 1 year, nearly 16h/day, 7 days a week, and I'm giving it for free. You need not to use it. So, I'd be thankful if you could point occasional failures politely rather than throwing me in a lava pit.
Thank you!
by LightMachine