Why didn't this author compare Llama 3 with GLM 5.2 (released 1 week ago) which is a more standard attention based LLM? To compare 2 separate families of LLMs and then pointing out that they are different is not a surprising result and detracts from the point the author is trying to make.
If you look at it, the diagrams are very similar, but the main differences are that the feedforward is replaced with a MoE (router to multiple feedforwards) and the model has a different attention implementation.
It's the bitter-lesson to feature-engineering lifecycle.
When a technique or technology is new people are making massive gains by just applying it to some use case, or gathering more data for training, or giving it more resources.
As time goes on those "bitter lesson" gains start to hit the shallow part of the logistic curve and companies have to start investing more and more effort into engineering for each small, incremental gain.
I assume the choice of phrase "bitter lesson" is intentional irony (since the original concept is that you get better results by just scaling up and not trying to be clever with domain-specific knowledge)?
My read was: "The first 90% of the work takes the first 10% of the time, and the remaining 10% of the work takes the other 90% of the time." And that we are now squarely in the remaining 10% of the work.
10 comments
[ 3.6 ms ] story [ 38.3 ms ] threadhttps://sebastianraschka.com/llm-architecture-gallery/?compa...
If you look at it, the diagrams are very similar, but the main differences are that the feedforward is replaced with a MoE (router to multiple feedforwards) and the model has a different attention implementation.
When a technique or technology is new people are making massive gains by just applying it to some use case, or gathering more data for training, or giving it more resources.
As time goes on those "bitter lesson" gains start to hit the shallow part of the logistic curve and companies have to start investing more and more effort into engineering for each small, incremental gain.
- https://ianbarber.blog/blogroll
- https://ianbarber.blog/archive
- https://ianbarber.blog/blog
- https://ianbarber.blog/posts
- none of the above links work
- i really dont want to scroll 200 pages just to see what your blog articles are
Nice, hadn't seen this one before.
But, I think the underlying problem is that we don't understand how this sh*t works. So, it's just an empirical, iterative mess.
Like physics in the the years shortly before relativity and quantum mechanics.