JoelEinbinder

My understanding is that existing rail lines aren't flat/straight enough for high speed rail. There's no point to a bullet train if it has to constantly slow down for corners/hills.

The benchmark shows lower ram usage on a very simple demo website. I expect that if the benchmark ran on a random set of real websites, ram usage would not be meaningfully lower than Chrome. Happy to be impressed and wrong if it remains lower.

When I've talked to people running this kind of ai scraping/agent workflow, the costs of the AI parts dwarf that of the web browser parts. This causes computational cost of the browser to become irrelevant. I'm curious what situation you got yourself in where optimizing the browser results in meaningful savings. I'd also like to be in that place!

I think your ram usage benchmark is deceptive. I'd expect a minimal browser to have much lower peak memory usage than chrome on a minimal website. But it should even out or get worse as the websites get richer. The nature of web scraping is that the worst sites take up the vast majority of your cpu cycles. I don't think lowering the ram usage of the browser process will have much real world impact.

Google's monorepo of closed source code.

Seems like Hyundai own 33% of Kia, rather than it just being a brand under the same company like Lexus/Toyota. They share some things and compete on others.

I think Hacker News might appreciate some of the behind the scenes of this post.

Getting this page to load quickly was not trivial. The initial dataset of books starting sentences was over 20 megabytes. By only sending the unique prefix of each book, I was able to get that to be much smaller. Using a custom format, sorting the prefixes, and gzipping got the size down to 114kb. About 3 bytes per book. The full first sentences are downloaded on demand as the books are filtered down.

Rendering the books requires 5 million triangles. I used WebGL 2's drawArraysInstanced method. This allows me to define the book geometry only once, and each book is just defined by it's rotation/position/color. Then it's just a matter of keeping the fragment shader simple.

Going into this project, I wasn't sure if it was possible. But I have left feeling really impressed with how capable the web is these days if you are willing to push a bit.

It would make competitive chess even more draw-ish. It is much easier to see when you accidentally get into a losing position than when you miss a winning idea. So the take back would be used defensively.

On the full set of 1000 questions, the language models are getting 30-35% correct. With patience, humans can do 40-50%.

The language models were prompted with the text + each candidate answer, and the one with the lowest perplexity was picked. I tried to avoid instruction tuned models wherever possible to avoid the "voice" problem.

What scores are you getting using this technique?

After the quiz, the source is linked along with the full comment.

The prompts you see in the quiz are from real hacker news comments. Whatever word the commenter said next is the "correct" word.

Temperature doesn't play a role here, because the LLM is not being sampled (other than to generate the candidate answers). Instead the answer the llm picks is decided by computing the complexity for the full prompt + answer string.