zlacker

[return to "For algorithms, a little memory outweighs a lot of time"]
1. whatev+ti[view] [source] 2025-05-21 21:31:16
>>makira+(OP)
Lookup tables with precalculated things for the win!

In fact I don’t think we would need processors anymore if we were centrally storing all of the operations ever done in our processors.

Now fast retrieval is another problem for another thread.

◧◩
2. EGreg+SE[view] [source] 2025-05-22 01:27:03
>>whatev+ti
You’re not wrong

Using an LLM and caching eg FAQs can save a lot of token credits

AI is basically solving a search problem and the models are just approximations of the data - like linear regression or fourier transforms.

The training is basically your precalculation. The key is that it precalculates a model with billions of parameters, not overfitting with an exact random set of answers hehe

◧◩◪
3. walter+Si1[view] [source] 2025-05-22 09:30:58
>>EGreg+SE
> Using an LLM and caching eg FAQs can save a lot of token credits

Do LLM providers use caches for FAQs, without changing the number of tokens billed to customer?

◧◩◪◨
4. EGreg+TI2[view] [source] 2025-05-22 19:29:12
>>walter+Si1
No, why would they. You are supposed to maintain that cache.

What I really want to know is about caching the large prefixes for prompts. Do they let you manage this somehow? What about llama and deepseek?

[go to top]