#Code

Hook fields that rewrite commands mid-flight, persistent agent memory, auto-mode rules in plain English, self-improving dream loops, and every example is copy-paste ready.

This is a blog post for my recent paper on RL post-training of LLMs: introducing the Matthew Effect and proposing to solve it with Never Give Up. It is presented interactively and less formally, more like how I give the talk.…

We watched almost 17k sessions across different types of personas, with 1,163 prompt variations, 75 repositories and 3 coding agents (Claude Code, Codex, Cursor) actually implementing the solutions instead of just recommending one.

A new wave of litigation focused on violations of municipal regulations is emerging against multifamily housing landlords, many of whom are facing antitrust litigation targeting their use of certain revenue management products.…

Agents can write code faster than we can absorb it. Here's why it still matters for humans to understand what they build — and some techniques for doing that efficiently: explainer docs, quizzes, micro-worlds, and shared spaces.

Splitting a finished branch into small PRs used to be the expensive part, so we decided the boundaries before the code existed. That cost collapsed. Now the code can tell you where to cut it.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

From the Zed Blog: A multiplayer environment for coding with agents, from the creators of Zed.

Includes background-clip for masking backgrounds, vertical-align for aligning elements, box-decoration-mode for consistent edge styling, letter-spacing for spacing control, and text-combine-upright for vertical text layouts.

Compilers have a hard time optimizing floating point math. Rust has a new API to fix this.

A technical deep dive into how GitHub Copilot handles context, recent edits, model routing, local session memory, and network requests.

As AI coding assistants shift the developer's primary role from writing boilerplate to reviewing and maintaining systems, language choice becomes critical for long-term architectural integrity.…

Oracle has banned AI-generated code from OpenJDK contributions, citing safety, security, and intellectual property risks. The open-source Java project steward said developers can use LLMs privately for debugging and reviewing code but cannot submit…

CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool injection, hardcoded secrets, and DMCA-flagged AI dependencies. - asamassekou10/ship-safe

Cloudflare OS is an open-source platform that lets everyone in your company build apps, automate work, and safely access internal systems, shaped around what your organization knows and how it operates.