What's the largest software project AI can complete on its own?
MirrorCode is Epoch AI's benchmark for long-horizon coding: AI can reimplement entire programs end-to-end, with no access to the original source code.
The latest blog posts to take off on Hacker News. 7,293 posts.
MirrorCode is Epoch AI's benchmark for long-horizon coding: AI can reimplement entire programs end-to-end, with no access to the original source code.
A universal document converter
The JFrog security research team recently identified a supply chain attack targeting the `xinference` package on PyPI. Versions 2.6.0, 2.6.1, and 2.6.2 were compromised and yanked by maintainers after users reported suspicious behavior. If you installed or imported these versions, you must assume your environment is…
Qwen offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
Want to follow along with Rust development? Curious how you might get involved? Take a look!
An interactive tour of what’s new in Go 1.27: every notable language, runtime, and standard library change, with short runnable examples you can edit and run in the browser.
An open-source multi-tag fully local UWB positioning system.
LocalAI is the open source AI engine. Run any model, LLMs, vision, voice, image and video, on any hardware. No GPU required.
Rune 1.1 makes Rune free for personal use and adds a perpetual commercial license, a workspace symbol index, first-class Python support, an Emacs editor, and substantial improvements to SSH workspaces.
Stacked pull requests break large changes into small, reviewable pull requests. They’re an ordered series of pull requests that each represent focused layers of your change. With stacks, you can…
A recap on the work done in NumPy and CPython to make multi-threaded NumPy workloads scale on the free-threaded build of CPython.
The 2026-07-28 Model Context Protocol specification is out, bringing a stateless protocol core, Multi Round-Trip Requests, header-based routing, cacheable list results, authorization hardening, a formal extensions framework, and updated Tier 1 SDKs.
Guide to the DeltaNet Family of linear attention mechanisms.
Started by rafalp on Dec. 12, 2023 in the Roadmap category. 6 replies, last one from July 25, 2024.
The next stable version of Ruff is out now.
We removed over 80% of Claude Code's system prompt for more advanced models. How to apply the lessons we learned to your own context engineering in Claude Code and with your own agents.
sqlite-backed shell history
Define a simple, standard API for parsing and generating JSON documents so that doing so does not require an external library. Enable many JSON processing tasks to be accomplished with little coding. This is an incubating API .
I always liked to see and touch the cover artwork of the CDs and LPs I bought in the past, but in the end the convenience of digital streaming won me over and I accepted no (or stamp-sized) artwork. Lately I’ve been missing this more and more and ultimately decided to try to do something about it. So I built a…
In a previous post SIMD Matters I discussed the big wins I got from graph coloring to make the contact solver faster. That same approach exists in Box3D. I like to call this approach “wide SIMD”. The idea is to process multiple work units at the same time. In the contact solver this means solving four contact points…
Bring reactive notebooks into your Python projects, without leaving your IDE
Or: the difference between vibe-coding and vibe-engineering.
After quite a long while, Hyprland 0.55 is upon us! This is an enormous update by each measurable metric - commits, contributors, features and changes.
The Wasm GC and exceptions proposals are both enabled by default in today’sWasmtime 47 release! We are excited to help bring more languages to WebAssemblyand everywhere that Wasmtime runs. Getting to this point involved large Wasmtimecha...
A tutorial Formal Verification using Lean for cryptographic engineers. Implement and prove correctness of the One-Time pad following a cryptography book.
⭐️ A friendly language for building type-safe, scalable systems!
On reward functions, dopamine, and what it actually feels like when the code starts writing itself
Turso is becoming the LLVM of databases: one modern, reliable Rust core with many SQL frontends. After rewriting SQLite, we are now building Postgres.
/prewalk hands the cheap model a trajectory, not a plan, retaining 92–97% of frontier pass rate at roughly half the cost on SWE-Bench Pro.