I was thinking about FizzBuzz and thought it might be cool to benchmark various LLMs to see the highest number they could go before they got it wrong. FizzBuzz is cool because you can test whether the model's can generalize to any other game (divisors of 3 and 7 instead of 3 and 5 for example).
Fun, short and sweet experiment to run over the weekend, with some mildly interesting results :)
Weird. I see the differences on mine across browsers and on my phone and desktop.
And yeah I get it, I don’t claim this to be something amazing that should shoot up in ranking, just that it was my first experience vibe coding. But it certainly works on my end! What about if you search for a google web font?
The differences are very subtle in lowercase, check uppercase? But maybe your system doesn't have Helvetica/Arial installed? I assumed its available on every OS, but that might not be the case.
Inspired by Jonathan Hoefler's essay that illustrated the problems with pangrams as typeface proofs, I wanted to build a simple site that lets you proof any font from Google Fonts with his proof texts. Almost all(~95%) of the site was built with Gemini CLI
Just wanna say this is a really cool project, and I can't think of higher praise than me hoping I build something as cool as this some day! I've been meaning to learn Go for sometime now, and will be referring to Zasper for the future :)
Most sentences in the world are not about truth or falsity. Training on a high quality corpus isn’t going to fix ‘hallucination’. The complete separation of facts from sentences is what makes LLMs powerful.
Slightly related to the task, I wanna plug in my utility app for finding LaTeX commands for characters, DeTeXt: https://venkatasg.net/apps/detext
I've gotten a lot of requests to do whole equations, but I feel that would massively increase the complication of the app for not that much benefit? How often do people want to convert a whole bunch of equations into LaTeX? My use case is usually writing my own equations and forgetting the command for a specific symbol, or looking for a symbol that looks something like X.
I've noticed that soundtracks show up in this Classical music app, so some (not all) of my Tamil songs (which are songs from movies because that's how most pop/commercial music in India is released) are listed there now.
I keep running into issues, even after installing Rust in my condo environment (using conda). Specifically the issue seems to be building wheels for `tokenizers`:
warning: build failed, waiting for other jobs to finish...
error: build failed
error: `cargo rustc --lib --message-format=json-render-diagnostics --manifest-path Cargo.toml --release -v --features pyo3/extension-module -- --crate-type cdylib -C 'link-args=-undefined dynamic_lookup -Wl,-install_name,@rpath/tokenizers.cpython-310-darwin.so'` failed with code 101
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for tokenizers
Failed to build tokenizers
ERROR: Could not build wheels for tokenizers, which is required to install pyproject.toml-based projects
I have licensed it under the MIT License like NetNewsWire. I honestly don't mind if someone makes something commercial from this - this app wouldn't have been possible without opensource software and data (from Detexify). I made this app mostly as a learning exercise, and to test my skills.
Thank you so much for the kind words! I don't think Apple would promote it because LaTeX means something completely different to most people haha.