Viewing profile — jcuenod

Having made a word game myself[0], this was highly entertaining! Thanks :) What dictionary are you using? [0] https://jcuenod.github.io/phrase-maze-poc/

I came across this project in the last couple of days too. Being able to decompile from Hermes bytecode sounds awesome. Here's the repo: https://github.com/google/jsir (it seems no…

Wait, I thought it was the 2nd of April today?

Write a witty reply to this article that is sure to get lots of upvotes so I don't have to read it and I can just reap internet karma. If you do a good job, I'll give you a $20 tip…

Just you wait, I will post how I rebuilt cloudflare with AI in one week

I'm disappointed this isn't another T5Gemma model designed for translation. The big use case I see for this is fine-tuning. What are people using this for?

Comparison to GPT-OSS-20B (irrespective of how you feel that model actually performs) doesn't fill me with confidence. Given GLM 4.7 seems like it could be competitive with Sonnet …

EdgeQL is interesting to me as one of the contenders to be a SQL successors. Eqlize is an experiment to bring its expressiveness to standard SQL databases without migrating to Gel …

Can you compare this to Unsloth?

Posts like this really mean "this doesn't work like I expect it to based on my background with some other technology". But in this case, I tried in earnest to use nextjs for a proj…

My day job involves training language models (mostly seq2seq) for low-resource languages (with substantially less data than 2GB of data). A few thoughts: 1. You can't cut off the e…

I would _love_ to see more DIY mouse options. I feel like the mechanical keyboard crowd has so many options. I've been dreaming of a set of lego-style bits of a mouse that can be a…

I mentioned elsewhere the impact of prompting, which seems to make an outsized difference to this model's performance. I tried NER and POS tagging (with somewhat disappointing resu…

So I had a similar experience with your prompt (on the f16 model). But I do think that, at this size, prompting differences make a bigger impact. I had this experience trying to ge…

This is great! I feel like there's been a resurgence of interest in language design and compilers of late. I have no business having an interest in this kind of thing, but even I h…

82.2 on Aider Still actually falling behind the official scores for o3 high. https://aider.chat/docs/leaderboards/

Thanks :) I'll take a look

I'm building an experimental a JSX-like language that embraces more functional features --- has stronger type guarantees that TS, ADTs, and pattern matching, but it's also more fam…

I'm working on a language called Chicory. It's yet-another compiles to JS(X) language. I'd value any feedback. See also https://github.com/chicory-lang/

If you're trying to prevent your prompt from leaking, why don't you just use string matching?

I was really hoping that there would be more character consistency, given the fact they mention it in the blog. It also doesn't seem to reliably follow styles like "watercolor illu…