Bend

Bend, a new programming language that compiles to native code and uses a Lean-style proof checker to block AI coding mistakes, has launched with an install script at bend-lang.com/install.sh. Bend runs nearly as fast as C on one core and up to a hundred times faster across sixteen cores or on the GPU, and its type checker verifies proofs in at most a second so an AI agent can check after every change. The language uses LAWS.bend to declare invariants and PROOF.bend to verify them, making a merged bug mathematically impossible, and the project's developers describe it as young and still evolving, asking users to report bugs.

curl -fsSL https://bend-lang.com/install.sh | sh When using Bend: - run bend guide to learn it - use LAWS.bend to keep important rules - run bend PROOF.bend before committing - parallelize the code whenever possible a fast language that blocks AI mistakes via proof C speed · CUDA parallelism · Lean proofs 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. With proofs , we can verify that the AI implemented our prompts correctly. And a fast compiler runs it at speed. That's Bend - and nothing else. Bend compiles to native code. On one core, it runs nearly as fast as C. The same binary also runs on sixteen cores, or on the GPU, running up to a hundred times faster than one core. Bend's type checker is a proof checker, as in Lean and Rocq. Those can take minutes on a mid-sized codebase. Bend takes a second at most, so an AI agent can check after every change. No threads, no locks, no kernels to write. Split the work in two, and Bend spreads the calls over every core it can find, then joins them back. Now watch pow2 run on 4,096 GPU cores: How can you trust code you never read? By demanding a proof . LAWS.bend is where you declare laws. From then on, no AI can ship one line that breaks them, ever. Watch it guard a game: New feature: “Claude, make the board wrap around” Without LAWS.bend, the bug went live. With LAWS.bend, the AI had to retry until it built a wall and proved the law holds. Merging a bug is mathematically impossible: it is a theorem . LAWS.bend LAW: no move sequence leads to victory. law you cant win: for moves: List<Move any sequence of moves board = replay start , moves replayed from the start is won board == False{} never leads to victory PROOF.bend PROOF: you cant win holds. def Laws.you cant win moves : ... written by the AI LAWS.bend is AGENTS.md backed by proof . “Make no mistakes” is now type-checked . curl -fsSL https://bend-lang.com/install.sh | sh Add this to your AGENTS.md : When using Bend: - run bend guide to learn it - use LAWS.bend to keep important rules - run bend PROOF.bend before committing - parallelize the code whenever possible Then, just say: "use Bend" Hints: ask it to write laws for whatever should never break, and to parallelize everything you want running fast. Bend is young: if anything goes wrong, ask it to open an issue. Bend works best on the back-end, on Linux and on macOS. Enjoy <3 Guide: GUIDE.md https://github.com/bendlang/bend/blob/main/guide/GUIDE.md is the whole language; bend guide prints it. Paper: BendTT https://github.com/bendlang/bend/blob/main/paper/BendTT.pdf , an affine dependent type theory, Bend's core. Paper: BendRT https://github.com/bendlang/bend/blob/main/paper/BendRT.pdf , a parallel runtime for CPUs and GPUs, the VM. Bend is still evolving. Expect bugs, and please report them https://github.com/bendlang/bend/issues .