Me: Can we browse the web in Evangelion NERV mode?
Nonbeliever: no
Vibe Stitcher:
Straight up mogging the DOM with Vibe Stitcher
Chrome extension + @stitchbygoogle = vibe-restyle any site in-browser
Saves local restyled versions, so the web matches your taste
Release soon
1
98
Straight up mogging the DOM with Vibe Stitcher
Chrome extension + @stitchbygoogle = vibe-restyle any site in-browser
Saves local restyled versions, so the web matches your taste
Release soon
Introducing the new @stitchbygoogle, Google’s vibe design platform that transforms natural language into high-fidelity designs in one seamless flow.
🎨Create with a smarter design agent: Describe a new business concept or app vision and see it take shape on an AI-native canvas.
⚡️ Iterate quickly: Stitch screens together into interactive prototypes and manage your brand with a portable design system.
🎤 Collaborate with voice: Use hands-free voice interactions to update layouts and explore new variations in real-time.
Try it now (Age 18+ only. Currently available in English and in countries where Gemini is supported.) → stitch.withgoogle.com
my takeaway from vibe coding this macOS app: web apps have a lot less friction
I see your use case @glazeapp
wanted to try Gemini Embeddings 2 on local files so built a lightweight client that runs on my macbook
no SaaS wrapper
bring your own Gemini API key
download the github release or build the app yourself on xcode
open source @ github.com/0xyard/vektra
thoughts 👇
1
48
wanted to try Gemini Embeddings 2 on local files so built a lightweight client that runs on my macbook
no SaaS wrapper
bring your own Gemini API key
download the github release or build the app yourself on xcode
open source @ github.com/0xyard/vektra
thoughts 👇
Introducing Gemini Embedding 2! Our first multimodal embedding model for text, images, audio, video, and PDFs.
Here's an app you can try in @GoogleAIStudio where you can see multimodal search in action:
Refactored it for non-training use case
The use case: find best compliments to tell my wife
Need accurate digital twins of wife and my voice as verifiers for this to produce better results
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:
- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)
The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.
github.com/karpathy/autorese…
Part code, part sci-fi, and a pinch of psychosis :)









