Join Notes
A batch of the best highlights from what Tristan's read, .
Similarly, if you give GPT-3 a task that's too complex to do in the time it takes to calculate its next token, it may confabulate an incorrect guess. Yet, akin to humans, that doesn't necessarily mean the model is incapable of the task. With some time and space to reason things out, the model still may be able to answer reliably.
openai-cookbook/techniques_to_improve_reliability.md
openai
I couldn’t have found God in the seminary, he thought, as he looked at the sunrise.
The Alchemist
Paulo Coelho
The public vigorously debated who was ultimately responsible, but almost no one suggested that it was the result dictated by the herd mentality of all involved.
...catch up on these, and many more highlights
Readwise