Join Notes
A batch of the best highlights from what Tristan's read, .
One might have thought that to have the network behave as if it’s “learned something new” one would have to go in and run a training algorithm, adjusting weights, and so on. But that’s not the case. Instead, it seems to be sufficient to basically tell ChatGPT something one time—as part of the prompt you give—and then it can successfully make use of what you told it when it generates text. And once again, the fact that this works is, I think, an important clue in understanding what ChatGPT is “really doing” and how it relates to the structure of human language and thinking.
What Is ChatGPT Doing ... And Why Does It Work?
Stephen Wolfram
Sometimes, it can be liberating to work on the most difficult problem first. It depends on how you write code. Tests help us make small baby steps and therefore help make difficult problems easier to solve.
Test-Driven iOS Development With Swift
Dr. Dominik Hauser
Logical fallacies are errors in reasoning or argumentation that can undermine the validity of an argument. They are often used to mislead or distract from the truth, or to win an argument by appealing to emotions rather than reason. It's important to be aware of these fallacies in order to critically evaluate arguments and avoid being misled.
Books About Logical Fallacies
logicalfallacies.org
...catch up on these, and many more highlights
Readwise