Coding is becoming a commodity.
Taste is not.
World-class products are built by teams with taste.
If you believe the same, come build with us at Zenact AI.
Hiring a Founding Product Designer
• 0-1 mindset
• ships daily
Send portfolio → [email protected]
do not lie to yourself that getting good will take time and practice(not saying that it wont), these are just lies you feed yourself to get more comfortable; "i need to become the best asap"
I’m not joking and this isn’t funny. We have been trying to have a baby since last year. There are various options, not everyone is aligned… I gave Claude Code a description of the problem, it impregnated my wife in an hour.
LeCun's JEPA has evolved into a vision-language model, with 1.6B parameters rivaling the 72B Qwen-VL.
Instead of predicting words directly, the proposed VL-JEPA learns to predict the core "meaning" of a text in an abstract space, ignoring surface-level wording variations.
This method outperforms standard token-based training with 50% fewer parameters. It beats models like CLIP & SigLIP2 on video classification/retrieval tasks and matches larger VLMs on VQA, while using a decoder only when needed to cut decoding ops by nearly 3x.
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
Paper: https://t.co/rGglBXvKex
Our report: https://t.co/TXEHRquSBr