Why would I believe that any of this works? This is just some blokes idea of what people should do.
There is no evidence offered. No attempt to measure the benefits.
There is no evidence offered. No attempt to measure the benefits.
As the author points out, many of the patterns are fundamentally about in-context learning, and this in particular has been subject to a ton of research from the mechanistic interpretability crew. If you're curious, I think this line of research is fascinating: https://transformer-circuits.pub/2022/in-context-learning-an...