What? Pre-training? No, no, no, no. No pre-training. Why would you do pre-training?!
If you do pre-training, people will ask "HOW MANY TOKENS?" And it will never be enough. The model that was the frontier breakthrough becomes "just distillation from chatgpt"
But if you just do SFT, some RL on benchmarks? You're efficient. You're doing *reasoning*.
It's not about capabilities, it's about the benchmark score. And who tops the leaderboard? Labs doing RLFT on a Chinese frontier base.
I don't understand why people aren't using AI for trading.
They could make more profits using AI.
Here is a list of tools that can be used for trading:
Google DeepMind, David Silver reveals:
we built a system that used RL to discover its own RL algorithms.
this AI-designed system outperformed all human-created RL algorithms developed over the years.