Join Notes
A batch of the best highlights from what Tristan's read, .
Using a few-shot prompt to extend or modify a fine-tuning dataset is an idea that can be generalized beyond explanation writing. For example, if you have large quantities of unstructured text that you want to train on, you may find opportunities to use a prompt to extract a structured dataset from your unstructured text, and then fine-tune a custom model on that structured dataset.
openai-cookbook/techniques_to_improve_reliability.md
openai
A classical mental mechanism, called anchoring, seems to be at work here. You lower your anxiety about uncertainty by producing a number, then you “anchor” on it, like an object to hold on to in the middle of a vacuum.
The Black Swan
Nassim Nicholas Taleb
One of those desirable difficulties is known as the “generation effect.” Struggling to generate an answer on your own, even a wrong one, enhances subsequent learning. Socrates was apparently on to something when he forced pupils to generate answers rather than bestowing them. It requires the learner to intentionally sacrifice current performance for future benefit.
...catch up on these, and many more highlights
Readwise