31–40 of 54 posts
Earlier quoted context omitted.
What are you basing how good they are on? Personal experience or some benchmarks?
Benchmarks, we have internal ones testing reasoning fine-tuned v/s frontier + prompts For some use cases it can be parity performance at 1/20th the cost up to exceeds at 1/10th the cost. Trade-off is ofc narrow applicability
Earlier quoted context omitted.
Yeah, my big problem with the paper is it just might be an artifact of qwen's training process.
In all fairness most of the unique stuff I can do is probably an artifact of my training process, so it seems unfair to deny an LLM the same accomodation.
Earlier quoted context omitted.
Except learning to reason is a far cry from curve fitting. Our brains have more than five parameters.
It's the statistics equivalent of 'no one needs more than 640kb of RAM'
I’m glad the rest of the anchor text gave some context.
This is interesting and all, but “LoRA” is painfully close to “LoRa” (which is related to radio networking, not AI) when just scanning a list of topics. We’re never going to beat the Shannon limit on acronyms and initialisms. I’m glad the rest of the anchor text gave some context.
This is interesting and all, but “LoRA” is painfully close to “LoRa” (which is related to radio networking, not AI) when just scanning a list of topics. We’re never going to beat the Shannon limit on acronyms and initialisms. I’m glad the rest of the anchor text gave some context.
> Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting.
This is interesting and all, but “LoRA” is painfully close to “LoRa” (which is related to radio networking, not AI) when just scanning a list of topics. We’re never going to beat the Shannon limit on acronyms and initialisms. I’m glad the rest of the anchor text gave some context.
I see this comment on every single LoRA post despite the vast majority of posts being about LoRA not LoRa. Can we please stop beating this dead horse?
This is interesting and all, but “LoRA” is painfully close to “LoRa” (which is related to radio networking, not AI) when just scanning a list of topics. We’re never going to beat the Shannon limit on acronyms and initialisms. I’m glad the rest of the anchor text gave some context.
A version of this comment is posted in all submissions about Low Rank Adapters. I don't see how "Learning to reason in 13 parameters" would apply to low power radio communication, so it's even less relevant this time. > Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting. https://news.ycombinator.com/newsguid…
I’m sorry if that reads like a complaint.