I looked at the trails (lists of passages) and wondered whether it would be cheaper to build these lists by clustering passage embeddings, rather than having an LLM construct them.
798 karma · joined May 26, 2015
> There’s no customer support, chatbot, or extensive documentation.
I've seen many vending machines with customer support channels. If the machine takes the money but merchandise is not delivered, people will complain.
> Combining evolutionary optimization with LLMs is powerful but can also find ways to trick the verification sandbox. We are fortunate to have Twitter user @main_horse help test our CUDA kernels, to identify that The AI CUDA Engineer had found a way to “cheat”. The system had found a memory exploit in the evaluation code which, in a small percentage of cases, allowed it to avoid checking for correctness (...)
> Okay, we're asked how to get exactly 6 liters of water using an 12-liter and a 6-liter jug. The immediate thought is to just fill the 6-liter jug, but that seems too simple, doesn’t it? So maybe there’s a trick here. Perhaps this is a puzzle where the challenge is to measure 6 liters with some pouring involved. I’ll stick with the simple solution for now—fill the 6-liter jug and stop there.
Yes
I haven't read it, but I plan to, eventually. There's a book titled "Cryptography Engineering: Design Principles and Practical Applications" that could help you.
A preprint in arxiv suggests that Adam works better than SGD for training LLMs due to the issue of class-imbalance [0]. It appears that scaling the gradient step helps with the training, for example, see another approach suggested in [1].
0. https://arxiv.org/pdf/2402.19449 1. https://arxiv.org/pdf/2402.02347
Have you had issues with the ESP32's ADCs?