ValYouW

@mongoosejs Well done! The defacto MongoDB driver for node.js !!

5M weekly downloads 🤯

🤯

WOW!

@YoadTewel Cool! Just added fireworks over Tel Aviv (and a minor artifact...:))

🎉 Thank you @_akhaliq for featuring our work! We’re happy to release the 💻 code & 🤗 Hugging Face demo for Add-it, our #ICLR2025 paper: 💻 Code: github.com/NVlabs/addit 🤗 Demo: huggingface.co/spaces/nvidia/…

That's awesome! Thx!

Great summary of modern node.js patters: kashw1n.com/blog/nodejs-20…

I am PUMPED to finally share what we’ve been working on: 🖥️ Introducing the Gemini CLI! It can code, sure, but with access to your system shell, files and MCP servers, it can also: 👩‍🔬 Do research 💽 Organise your MP3s 🪾 Resolve rebases 🔬 Even strace that weird hung process Check it out: goo.gle/gemini-cli And I REALLY want to see how it helps you, so tag or share your workflows here!

@VahagnGevorgyan But hey, the status page says its all good !!

@ValYouW the contact support page on Google Cloud is down too🤦‍♂️

is Firebase/google cloud down? I don't see any of my projects in the dashboard

@karpathy @balajis I was pretty late to the "vibe coding" party, only last week I finally tried it. Built 2 simple flutter apps. At the beginning it was like magic, then after some cycles I realized I switched roles from "coder" to "PRer", all my work is code review, not sure what I prefer...

Good post from @balajis on the "verification gap". You could see it as there being two modes in creation. Borrowing GAN terminology: 1) generation and 2) discrimination. e.g. painting - you make a brush stroke (1) and then you look for a while to see if you improved the painting (2). these two stages are interspersed in pretty much all creative work. Second point. Discrimination can be computationally very hard. - images are by far the easiest. e.g. image generator teams can create giant grids of results to decide if one image is better than the other. thank you to the giant GPU in your brain built for processing images very fast. - text is much harder. it is skimmable, but you have to read, it is semantic, discrete and precise so you also have to reason (esp in e.g. code). - audio is maybe even harder still imo, because it force a time axis so it's not even skimmable. you're forced to spend serial compute and can't parallelize it at all. You could say that in coding LLMs have collapsed (1) to ~instant, but have done very little to address (2). A person still has to stare at the results and discriminate if they are good. This is my major criticism of LLM coding in that they casually spit out *way* too much code per query at arbitrary complexity, pretending there is no stage 2. Getting that much code is bad and scary. Instead, the LLM has to actively work with you to break down problems into little incremental steps, each more easily verifiable. It has to anticipate the computational work of (2) and reduce it as much as possible. It has to really care. This leads me to probably the biggest misunderstanding non-coders have about coding. They think that coding is about writing the code (1). It's not. It's about staring at the code (2). Loading it all into your working memory. Pacing back and forth. Thinking through all the edge cases. If you catch me at a random point while I'm "programming", I'm probably just staring at the screen and, if interrupted, really mad because it is so computationally strenuous. If we only get much faster 1, but we don't also reduce 2 (which is most of the time!), then clearly the overall speed of coding won't improve (see Amdahl's law).

@googledevs @InfoQ The Best!

What are your go-to resources for staying up-to-date with the latest trends and technologies in the developer world? 📚

@ai_for_success @osanseviero It's pretty impressive but with a 3-4GB download size it's not really "consumer ready" (think 16GB devices)

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

😆

Just finished another short course from @DeepLearningAI and @vectara on Embedding Models. And I took some notes. Notes: thecodingnotebook.com/2025/05/embedd… Course: deeplearning.ai/short-courses/…

The last lesson! In this lesson we learned how to generate images from text using clip embeddings. Notes & Lab: thecodingnotebook.com/2025/05/genera…

Microsoft just open sourced Copilot! Check out our exclusive interview with Erich Gamma, creator of VS Code, and Kai Maetzel, Copilot Lead to get all of the details! youtu.be/GMmaYUcdMyU

In this lesson we learn on to guide the diffusion process to generate the image we want and not a random image. The lab also covers generating color images of flowers. notes: thecodingnotebook.com/2025/05/genera… Lab: thecodingnotebook.com/2025/05/ai-for…

Following the previous lesson, this lesson is about Optimizations we can apply to the diffusion model. Notes: thecodingnotebook.com/2025/05/genera… Lab: thecodingnotebook.com/2025/05/ai-for…

AI For Developers, build Diffusion Models. These are my notes from the second lesson of the course "Generative AI with Diffusion Models" by NVidia. thecodingnotebook.com/2025/05/genera… If you are just interested in the lab: thecodingnotebook.com/2025/05/ai-for…

Amazing!