It's all react! Super composable and ready to use pic.twitter.com/ElSgEZ0Ocm
— Pietro Schirano (@skirano) 11 juillet 2025
It's all react! Super composable and ready to use
CODE
-
React AI Library: Composable and Ready to Use
By
–
-
Composable Code for Easy Project Integration
By
–
Everything you do is code, and we made it so that it's composable and as easy as possible to drop into any project. pic.twitter.com/lSvCrHJFBM
— Pietro Schirano (@skirano) 11 juillet 2025Everything you do is code, and we made it so that it's composable and as easy as possible to drop into any project.
-
Vision VAE as Ultimate Tokenizer: Unicode Efficiency
By
–
Very cool work direction but also fair question.
I wonder if ultimately is a little vision patch VAE the ultimate "tokenizer"? Unicode + UTF-8 is just too high description length. -
Building AI Tools with Lovable’s Agent Mode
By
–
Things I've built with @lovable
's agent mode recently:
– Custom Stripe invoice maker
– UI for my AI podcast cohost that includes speech to text (from me) and text to speech (from her)
– Audio-reactive visualizer for the AI above Lovable was already but agent mode is -
Open Source Non-Reasoning Model Achieves Competitive Performance
By
–
Nuevo super modelo de programación no-razonador, que logra unos números muy competitivos colocándose como el mejor modelo open source de este tipo! Eso sí, 1 trillion de parámetros así que olvidaos de ejecutarlo en local fácilmente. Aún así un regalo brutal para la comunidad
-
Years of sleepless nights yield invaluable AI engineering results
By
–
sleepless nights, years working in AI engineering and design. cost: immeasurable
result: invaluable. -
Handling Research Errors: Retractions and Code Fixes
By
–
i guess it depends on the nature of the issue. like how would that happen? if the conclusion of the paper changed, in the worst case, i guess pursue some kind of formal retraction more likely it'd just be a bug in the code in which case i'd rerun experiments then update arxiv
-
Model Training Results Improved to 94% Perfect Embedding Inversion
By
–
i was happy to see that the results held up! and i forgot that i trained the models a bit longer after the paper was submitted so they actually got somewhat better (94% perfect embedding inversion!)