https://arxiv.org/abs/2606.00206
In this paper they nerf an LLMs ability to emit waffling thinking tokens like "wait", "but", "alternatively", and the models (they're old, small models in the paper) terminate reasoning faster and perform better. I bet Anthropic is tuning this on their backend.
This is super cool. Do you know if any of the inference backends (llama.cpp, vllm, etc) support this technique?