updated 3mo ago
Tips for probabilistic software - jxnl.co
- Learning to focuson process and accept the periodic and inevitable bad outcomes is crucial.Great investors recognize another uncomfortable reality about probability: the frequency of correctnessdoes not really matter (batting average), what matters is how much money you make when you are rightversus how much money you lose when you are wrong (slugg... See more
from Reflections on the Ten Attributes of Great Investors by Dan Callahan
Daniel Bakalarz added
- Thinking about inputs and outputs to the system in a method-agnostic way lets you take a step back from the algorithmic jargon and consider whether other fields have developed methods that might work here using different terminology.
from How to Understand ML Papers Quickly by Eric Jang
Ian Vanagas added
- Some tasks are easier to improve via system design. While LLMs appear to follow remarkable scaling laws that predictably yield better results with more compute, in many applications, scaling offers lower returns-vs-cost than building a compound system. For example, suppose that the current best LLM can solve coding contest problems 30% of the time
... See morefrom The Shift From Models to Compound AI Systems by Matei Zaharia, Omar Khattab, Lingjiao Chen, et al.
Nicolay Gerold added