The author claimed that the models he modified with this layer repetition method topped the huggingface open llm leaderboard in his first post: https://dnhkng.github.io/posts/rys/
Do you remember the names of the previous experiments done on this? Would love to take a look.
Very interesting! I see that you've made a comment saying the other stuff you've tried is on the way as a second blog post, but what happens when you repeat these 7 layers once more? Does performance increase the more repetitions you do?
I think the big differentiator for this one is the carrying capacity. They list 50kg instant/30kg sustained carrying capacity which is very impressive and I can't think of other humanoids with similar capability off the top of my head.
The connections are too easy to the point where the main challenge for me was to remember/locate where I had stored the nodes of that category. I think the fun in a connection puzzle comes from trying to figure out what the link is that connects different nodes, and resolving any red herrings by deduction (which is what makes OnlyConnect's connection wall great and NYT's knockoff mediocre). In this one I can spot the intended category for each node without even looking at the others.
Have you actually completed it? There are plenty where the category is obvious, sure - but also many ambiguous entries. It's not trivial to fully complete if you're aiming to keep errors low!
E.g. in ROT13: Cuvynqrycuvn pbhyq unir orra n zrzore bs "H.F. Pvgvrf", "Purrfrf", be "Gbz Unaxf zbivrf"
That aspect makes it kind of a massively parallel "startup name or fantasy sword" challenge, once you get past the obvious ones (whether that helps or hinders I wouldn't claim either way, but it rhymes?)
reply