Get the latest tech news
Post-training 4B model with RL to fly Tesla Roadster 21% better than GPT-6 Astra
We RL-trained Qwen3-4B to fly a simulated flying Roadster. In storms, it beats DeepSeek, Muse, Beam, Nemotron and GPT-6 Astra, even when they get unlimited time to think.
None
Or read this on Hacker News
