Viewing profile — leod

Happy to see people working on vector search in Rust. Keep it up! As far as HNSW implementations go, this one appears to be almost entirely unfinished. Node insertion logic is miss…

This is a fair point and also called out in the discussion section. To some degree, this could be mitigated by hotloading shader code (and compiling shaders in debug mode). However…

Awesome work. Would you be willing to share details about the fine-tuning procedure, such as the initialization, learning rate schedule, batch size, etc.? I'd love to learn more. B…

Interesting. They train an image classifier to detect images that were generated by a GAN-trained CNN. I wonder if it could be possible to include this classifier in the training l…

Ha! In the model's defense, its training data [1] ends in 2017 -- not sure if hatred for Electron was as prevalent back then. [1] https://archive.org/details/14566367HackerNewsComm…

Thanks! I actually planned to make results shareable at the start, but, knowing the internet, I did not like the idea of being held responsible for whatever content (say offensive …

I've trained a Transformer encoder-decoder model (this was slightly before GPT2 came out) to generate HN comments from titles. There is a demo running at https://hncynic.leod.org

Thank you so much for your comprehensive answer, this helps a lot. If I understand nshepperd's code correctly, it uses a constant and small learning rate. Do you know if this works…

I haven't heard of gradient checkpointing yet, thank you for the link! Do you know how it compares to gradient accumulation? The latter basically reduces the batch size, but takes …

If humans are not limited by the halting problem, it would be great if you could tell me if the following function f halts for all integers n: https://gist.github.com/leod/9b89af30…

Thank you! The model weighs in at 1.2GB with 100M parameters, which is similar to the smallest GPT-2 model. I wouldn't be suprised if GPT-2 small (+ finetuning on HN data) performe…

This is true for some scenarios, like invalidating iterators through deletion (detected at compile-time by the borrow checker), but other scenarios still require runtime checks, ri…

This analysis seems to be based on some notion of "Cognitive Complexity", but I can't find its definition in the article. Am I missing something?

True, but that does not show that the approximation can always be learned from examples, does it?

That's certainly an interesting idea, but wouldn't some people just "reply all" for more visibility?

It certainly struck me as an odd analogy. There are plenty of theories that are hard to disprove, why choose one as politically loaded as "Marxism"?

I quite enjoyed The User Illusion (the author has a great way of looking at the world). I think its chapters on consciousness are mostly about what consciousness gets to see. Build…

I'm a Vim user as well, and when I tried Colemak for a few months some years back, Vim was what made me go back to QWERTY. It was just too awkward as I would like to be able to wor…

Maybe they believe that there is a higher long-term profit in having well-educated workers.