AI model OpenScholar synthesizes scientific research and cites sources as accurately as human experts

Keeping up with the latest research is vital for scientists, but given that millions of scientific papers are published every ...

Qwen3-Coder-Next offers vibe coders a powerful open source, ultra-sparse model with 10x higher throughput for repo tasks

On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside ...

OpenAI picks up pace against Claude Code with new Codex desktop app

By launching a desktop app, OpenAI is catching up to Anthropic’s popular Claude Code, which already offered a macOS version.
GitHub

A battle-tested starter kit for building open-source and internal NuGet libraries, born from half a billion downloads.

A bunch of dotnet new templates to quickly get you started building high-quality binary or source-only open-source and non-open-source libraries including everything you need to publish it on NuGet or ...

I tried a Claude Code alternative that's local, open source, and completely free - how it works

I was curious if Block's Goose agent, paired with Ollama and the Qwen3-coder model, could really replace Claude Code. Here's how I got started.

I tested local AI on my M1 Mac, expecting magic - and got a reality check instead

At random, I chose glm-4.7-flash, from the Chinese AI startup Z.ai. Weighing in at 30 billion "parameters," or neural weights, GLM-4.7-flash would be a "small" large language model by today's ...