OpenAI's Codex Plugin Lets Claude Code Users Get a Second AI Opinion
OpenAI published an open-source plugin that lets Claude Code users invoke Codex for reviews, background tasks, and session handoffs with slash commands.
20 stories
OpenAI published an open-source plugin that lets Claude Code users invoke Codex for reviews, background tasks, and session handoffs with slash commands.

An open-weights Mixture-of-Experts model gets fine-tuned on 8,000 Claude Opus 4.7 reasoning traces, porting frontier chain-of-thought style into Apache 2.0 weights.

A new optimization framework shows convergence speed depends on the local geometry an algorithm actually traverses, not worst-case bounds over the entire space.

A community-built terminal coding agent wired to xAI's Grok API, with sub-agents, sandboxed verification, Telegram remote control, and X search built in.

HauhauCS abliterates Qwen3.6-35B-A3B and ships it as GGUF with 0 refusals out of 465 tested prompts, pulling nearly 3 million downloads

NVIDIA's new Lyra 2.0 turns a single photo into an explorable 3D world, exportable to Isaac Sim and real-time renderers.

OpenAI released a 1.5B-parameter open-weight token classifier that detects and redacts PII locally, scoring 96% F1 with a 128K context window.

Alibaba's Qwen3.6-35B-A3B-FP8 ships a memory-efficient quantized checkpoint for a frontier-class coding agent that runs on a single GPU

A new framework treats 3D scene layout as an autoregressive geometry problem, hitting 19% better physical plausibility and 65% faster inference than the prior state of the art.

Genentech's Prescient Design team built RL environments for drug design tasks, then post-trained a 30B model that matches GPT-5 and Claude Opus.

A new Mila study puts the sharpening hypothesis head to head with task rewards in a unified RL framework, and one clearly wins.

A free, GPL-3.0 desktop app wraps Whisper and pyannote for fully offline interview transcription with speaker diarization and a built-in editor.

A landmark character animation research framework is leaving Unity behind, with a Python rewrite that unifies training, inference, and visualization.

Vercel's open-source Next.js chatbot template hits 20.9k stars, shipping artifacts, multi-model routing, auth, persistence, and Playwright tests out of the box.

Hugging Face's Rust-based embeddings server delivers up to 3x throughput over ONNX with dynamic batching, Flash Attention, and support for Qwen3, ModernBERT, and Gemma3.

A new agentic framework strips the answer out of theorem-proving benchmarks and forces AI to find it first, revealing a huge reasoning gap.

A new framework trains a 11.5-billion parameter atomistic foundation model on two exascale supercomputers, hitting 1.2 EFLOPS and cutting weeks of training down to hours.

CAMEL-AI's OWL framework crossed 19,000 GitHub stars while topping the GAIA benchmark for open-source multi-agent systems with a 69.09 average.

Z-Lab's DFlash draft model turns Qwen3.6-35B-A3B into a much faster server by drafting blocks of tokens with a tiny diffusion model.

SinRef-6D estimates the 6-DoF pose of unseen objects from a single RGB-D reference view, powering a robotic grasping system with 85% success.