Join Notes
A batch of the best highlights from what Tristan's read, .
The more you think about it, the more fluid and intractable it all becomes. Fictional characters act agentically, but they’re at least implicitly puppeteered by a virtual author who has orthogonal intentions of their own. Don’t let me get into the fact that all these layers of “intentionality” operate largely in [indeterminate superpositions](https://generative.ink/posts/language-models-are-multiverse-generators/#multiplicity-of-pasts-presents-and-futures).
Methods of meditation are effective only insofar as, through failure of dogged persistence, they show that the ego and its willing are unreal.
If you apply this technique to your own tasks, don't be afraid to experiment with customizing the instruction. `Let's think step by step` is rather generic, so you may find better performance with instructions that hew to a stricter format customized to your use case. For example, if you were you can try more structured variants like `First, think step by step about why X might be true. Second, think step by step about why Y might be true. Third, think step by step about whether X or Y makes more sense.`. And you can even give the model an example format to help keep it on track, e.g.:
openai-cookbook/techniques_to_improve_reliability.md
openai
...catch up on these, and many more highlights
Readwise