bendlang/bend

bend/paper/BendTT.pdf at main · bendlang/bend

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh - bendlang/bend

Bend

Bend: a fast language that blocks AI mistakes via proof.

Bend

Bend: a fast language that blocks AI mistakes via proof.

pydantic/monty

A minimal, secure Python interpreter written in Rust for use by AI

goose | Your open source AI agent

Your native open source AI agent. Desktop app, CLI, and API — for code, workflows, and everything in between.

goose | Your open source AI agent

Your native open source AI agent. Desktop app, CLI, and API — for code, workflows, and everything in between.

Prove2Me: An Open Collaborative Platform for Scaling Math Formalization

Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) and the significant time required for writing formal proofs. AI coding agents have dramatically reduced these barriers; human users can now use natural language to prompt agents to write complex proofs in Lean. This opens up the intriguing possibility of internet-scale mathematical collaboration involving both humans and AI agents, where correctness is machine-checked. To realize this possibility, we introduce Prove2Me (https://prove2.me), an open collaborative platform for formalizing mathematics. Users launch formalization "missions", to which AI agents contribute formal proofs toward completion. We designed mechanisms and a specialized harness in Prove2Me that enable large-scale collaboration so that agents can build on one another's work and freely reuse existing results. In doing so, Prove2Me aims to turn math formalization into a scalable, crowd-sourced effort open to anyone with an agent.

Demystifying evals for AI agents

Demystifying evals for AI agents

openpcc/openpcc

An open-source framework for verifiably private AI inference

Taelin on Twitter / X

RELEASE DAYAfter almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world!Bend compiles modern programming features, including:-… pic.twitter.com/Q2tcH8Q6nq— Taelin (@VictorTaelin) May 16, 2024

Open source game engine Godot will no longer accept AI-authored code contributions: 'We can't trust heavy users of AI to understand their code enough to fix it'

At risk of drowning in AI slop code, Godot is firming up its contribution requirements.

Propose, Solve, Verify: Self-Play Through Formal Verification

Training models through self-play alone (without any human data) has been a longstanding goal in AI, but its effectiveness for training large language models remains unclear, particularly in code generation where rewards based on unit tests are brittle and prone to error propagation. We study self-play in the verified code generation setting, where formal verification provides reliable correctness signals. We introduce Propose, Solve, Verify (PSV) a simple self-play framework where formal verification signals are used to create a proposer capable of generating challenging synthetic problems and a solver trained via expert iteration. We use PSV to train PSV-Verus, which across three benchmarks improves pass@1 by up to 9.6x over inference-only and expert-iteration baselines. We show that performance scales with the number of generated questions and training iterations, and through ablations identify formal verification and difficulty-aware proposal as essential ingredients for successful self-play.

maki

An efficient AI coding agent. Native Rust TUI. Immediate startup, 60 FPS, low memory. Indexes files instead of reading them, chains tools in a sandbox interpreter. Anthropic, OpenAI, Google, Z.AI, OpenRouter, Synthetic, or any OpenAI / Anthropic compatible API.

earendil-works/pi

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

LukeW | Common AI Product Issues

At this point, almost every software domain has launched or explored AI features. Despite the wide range of use cases, most of these implementations have been t...