GPT-6 Astra edited Qwen’s weights and raised MATH-500 from 7.9% to 48.1% in author-run tests. How weight-space programming works—and its limits.

Tsinghua’s HarnessPro cuts AI coding agent costs 26% while boosting accuracy without model retraining. Factory Droid 1.0 ...

Build a Cursor SDK agent in TypeScript with token budgets, a read-only toolset, cloud PR fixes and GitHub Actions. 12 steps, ...

Anthropic recently detailed how it migrated its monorepo from Git to Scion. Scion is a source control system that moves repository operations to the server side and uses content-addressed storage and ...

Artificial intelligence is widely used to develop software, analyze research, and improve the tools that power the technology itself. Recursive, an AI startup focused on building systems that can ...

AI can write code that runs. CS coursework tests whether you understand it. Here's where AI code fails and how to check it before you submit.

Recursive Flint is a 40B MoE local coding model with 2.5B active parameters, scoring 74.2% on SWE-bench Verified.

Recursive, an AI startup founded last year, is starting to live up to its name. The company, which is trying to build AI that can improve itself, released its first model, Flint, on Wednesday. Flint ...

When I asked an AI what it finds beautiful, it returned four lines of Python code.When you create a piece of work, you want ...

For the past few days I’ve been testing an impressive open-weight AI coding model called Flint. It suggests that fully recursive self-improvement, or RSI—an exciting and controversial approach that ...

When studying programming, you notice something strange.Processes that are extremely complex for humans to think through can sometimes be written surprisingly concisely using functions.A prime example ...

Video-RSI improves video understanding agents by evolving their executable harnesses while keeping model weights frozen. The Editor investigates training failures by revisiting videos, then turns the ...