- paraph1n parentCould someone point me towards a good resource for learning how to build a RAG app without llangchain or llamaindex? It's hard to find good information.
- 3 points
- How does it compare to zapatos?
- > "Critical" has a precise meaning in these kinds of systems; it essentially means when correlation lengths diverge (or, with a finite brain, become the size of the whole).
If someone doesn't know what "critical" means, they also don't know what a "correlation length" is, so I don't think this clarification is very helpful. Who was the intended audience?
- Can someone explain? I can barely parse this quote. Who are the 1P devs? Why does it matter that they didn't notice they had made a minor change? Why were they "tricked"?
Edit: I think I might understand it more now: This person got tricked into carefully reviewing the "entire" code, instead of focusing on the one minor change that was made to it, because they didn't realize it was only the minor change they had to review. In their careful review of the code, they uncovered vulnerabilities which were actually related to the original code (ie. VSCode) rather than the changes that this person was asked to review. Did I get it? I'm still confused about the use of "1P" here though.
- In order to understand the difference, you'd have to have a blinded and unblinded study, and compare the results. Then you could understand the difference between a guess with 90% confidence and actually knowing what treatment you received with certainty.
It seems reckless to presume the difference (between blinded and unblinded) is small. The numbers you cite (94.7% and 90% confidence) have nothing to do with the question you're trying to answer.
For example, an important difference may be with respect to expectations. If you're told you're receiving a psychedelic treatment, you may go into the experience with different expectations than if you were unsure about what treatment you were getting.
- Citation needed. They host their source on GitHub [1].
- > I recall from school the equipartition theorem-- 1/2 KT of kinetic energy for each degree of freedom. These things obviously have many degrees of freedom. So wouldn't they be "thrashing around" like rag doll in a blender at room temperature?
It's funny you say that, because the first image on the English Wikipedia page for Equipartition Theorem[1] is an animation of the thermal motion of a peptide.
- Sharp seems reasonable, but I've never heard someone use it to describe garlic in isolation. I've only heard people use it when describing garlic flavor as part of a dish eg. "This pasta has a sharp garlic flavor".
Fresh raw garlic really burns, and I think it's quite normal to describe it as hot or spicy in American English.