_venkatasg
Joined 8 years ago
Karma
288
Submissions
64
Member since
May 16
Recent submissions
Comment · 8 months ago
I got this silly idea for a benchmark and decided to test how well models do. Repo here: https://github.com/venkatasg/fizzbuzz-bench
Comment · 10 months ago
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 :)
Comment · 1 year ago
SHould have double checked Windows default fonts — Windows doesn't have Helvetica ugh.
Comment · 1 year ago
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?
Comment · 1 year ago
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.
Comment · 1 year ago
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
Comment · 1 year ago
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 :)
Comment · 2 years ago
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.
Comment · 3 years ago
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.