Viewing profile — 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 th…

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 bro…

Google's monorepo of closed source code.

I added Python support into my terminal, and then split it out into its own website as a REPL powered by Pyodide. It has autocomplete, expandable objects, syntax highlighting, inli…

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 …

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 wo…

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 candi…

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 …

If I used old comments then it's likely that the models will have trained on them. I haven't tested if that makes a difference though.

The language model generating the candidate answers generates tokens until a full word is produced. The language models picking their answer choose the completion that results in t…

The LLM didn’t generate the next word. Hacker News commenters did. You can see the source of the comment on the results screen.

If you want to practice it one question at at time, you set the question count to 1. https://joel.tools/smarter/?questions=1 When I tested it this way it resulted in less of an emo…

That isn't how it's supposed to work. I mean sometimes you get a supper annoying prompt like ">", but if you guess the right answer it should give you the point. I just checked the…

I made a little game/quiz where you try to guess the next word in a bunch of Hacker News comments and compete against various language models. I used llama2 to generate three alter…

You can set `pipe` to true in puppeteer (default false) here https://pptr.dev/api/puppeteer.launchoptions By default, Playwright launches this way and you have to specifically enab…

I'm not going to invest a drug company with a 90% chance of failure unless I can expect to get a 10x return if it succeeds.

Interesting to me that WebKit gets vertical form controls before MacOS. I don't have any experience with vertically written languages. How important are these controls to computer …