924 karma · joined May 16, 2017
Curious how this ages.
Recursive self improvement, self-play and multi-agent RL could make useful new theories, eventually.
"Much recent work on auto-research, self-improving agents, and evolutionary program search can be organized around this question. Other work on model self-play, synthetic data, test-time training and a broader theme of continual learning also matches the RSI vision (e.g. Yuan et al. 2024, Chen et al. 2024), Zhao et al. 2025, Choi et al. 2026)) but they will not be the focus of this post."
Bullet Physics author.
Hakko FM2023-05 Mini Hot Tweezers Kit or Hakko FX8804-02 Hot Tweezer for Hakko FX-888 for example.
>> I wish there was some way to switch tips that didn't involve letting it cool down
I replace tips while hot: the sleeve is not hot.
For example: https://github.com/StafaH/mujoco_warp/blob/render_context/mu...
(A new simple raytracer that compiles to cuda, used for robotics reinforcement learning, renders at up to 1 million fps at low resolution, 64x64, with textures, shadows)