Join 📚 Siddish's Favorites
A batch of the best highlights from what Siddish's read, .
Engineering isn't about building a paperclip that will never break, it's about building a paperclip that will bend enough times to get the job done, at a reasonable price, in sufficient quantities, out of attainable materials, on schedule.
Some Ideas on More Safely Prototyping LLM Products
daveguarino.com
7. Write Before Action
• @Conaw writes down what he plans to do, and how he plans to do it (in detail) before he does it
• "Why? Because sometimes I realize as I am halfway through writing things out that there is a fundamentally better approach."
• So simple. Rarely done
THREAD: The Top 0.1% Of...
@george__mack on Twitter
Naval: David Deutsch says conjecture plus criticism drive science. Matt Ridley says trial and error drives innovation. Others say variation and selection drive evolution.
These are variations on a theme: try a lot of stuff, get feedback, see what works, and stick with that.
A Distillation of What @...
@jmikolay on Twitter
...catch up on these, and many more highlights
Readwise