That's cool. I tried the b64 thing on my local qwen3.5 27b without access to tools and it did it.
Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
31–40 of 137 posts
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#32Isn't this similar to models that have "double check the answer"? First pass runs your input through, second pass runs it's output as input? Just, in double check it presumably runs the entire stack while you're trying to skip the translation steps and only double check the logic?
I don't think its mathematically equivalent or even close because the context/logprobs will be very different, since you only produce 1 token per pass. I'd say the token itself has a lot less information than the signal propagating through the residual stream of transformer blocks.
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#33[flagged]
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#34Is this similar to send 48656c6c6f2c20686f772061726520796f753f in the prompt? As done here: https://youtu.be/GiaNp0u_swU?si=m7-LZ7EYxJCw0k1-
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#35Thank you so much for sharing this in a delightful blog post. One of the more enjoyable things I've read in a while. Very motivating!
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#36Thanks for the post, really cool stuff you did!
Extra thanks for making it written in a readable and approachable way! I don't have much of a background in this topic, but still managed to understand about 70-80% of it :) You're a good writer
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#37[flagged]
A 5 hour old account with a standard chatgpt reply? Seriously, try harder.
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#38I think you may have cracked latent space reasoning. I've had a hunch that something like this would work, but couldn't figure out how the training would back propagate. But you've shown that you just need to duplicate existing layers. Have you tried a simple inline loop over the duplicated layers? Would be interesting to see performance. Also, would be interesting to compare with a MOE model. See if these layers are…
This is kind of what LoopLM is doing, no? https://arxiv.org/abs/2510.25741
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#39[flagged]
Have a look at the boundaries in the heatmaps. They are of course open to interpretation, but it suggest to me that the models develop 'organs' for processing different types of data, and without duplicating the 'whole organ' you don't get the benefits. This is quite different to what you usually see, which is via layer ablation experiments. Thoughts?
Maybe you are observing artifacts of Qwen's training procedure. Perhaps they initialized further layers with the weights of previous ones as part of the training curriculum. But it's fun to imagine something more exotic.
Re: Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
#40Wild stuff and great read
Do you think karpathy's autoresearch would be useful here?