Nilay Yadav

I checked my Claude history. A lot of what I type isn't questions. It's context. Backstory. Pasted emails. I'm doing the AI's job for it. So I built Contextify

@llom2600 thanks man, really appreciate it :) Open sourcing it soon!

@ynnilay Looks great!

I checked my Claude history. A lot of what I type isn't questions. It's context. Backstory. Pasted emails. I'm doing the AI's job for it. So I built Contextify

@DhruvAtreja1 means a lot 🙏 open sourcing it soon too!

@ynnilay This looks really useful😁

If you've ever pasted the same thread 3 times in a week - this is for you. Free. Mac only (for now). ctxify.dev @swyx @levelsio @theo @vipulved @ClementDelangue @mernit @patrickc

But doesn't Claude Memory already solve this? Kind of. It only works if you tell Claude the context in your chat. Contextify pulls the context for you. From the source. Automatically. You stop being the middleman. @AnthropicAI @alexalbert__ @karpathy @bcherny

@mernit a second brain app feels like the perfect use case for this..kinda realizing a personal memory app is the exact right thing to build with this

For the past few months, I’ve been running an AI swat team. We learn about a company, audit their workflows, and build them an AI app to automate their busywork. This sounds straightforward, but building these apps is annoying because you keep rebuilding the same things over and over: a filesystem, sandboxes per user, auth, streaming, and connections to messaging apps like Telegram and Slack So today we’re releasing all of it together in a batteries-included Python framework called Capsule It includes a sandboxed computer, multi-channel messaging, background jobs, multi-user auth, and payments – everything you need to ship a production-ready AI product super fast The faster you ship, the more you’ll learn from real customers, and the sooner you get PMF

@mernit those blue gpu glows giving full main character energy

dudes will really spend five thousand dollars and build a computer to run openclaw instead of getting a digital ocean droplet for $1.57 per month

📢 Open-sourcing the Sarvam 30B and 105B models! Trained from scratch with all data, model research and inference optimisation done in-house, these models punch above their weight in most global benchmarks plus excel in Indian languages. Get the weights at Hugging Face and AIKosh. Thanks to the good folks at SGLang for day 0 support, vLLM support coming soon. Links, benchmark scores, examples, and more in our blog - sarvam.ai/blogs/sarvam-3…

probably the best @modal use case -- serverless browser for your agents. on demand, connect anything playwright, puppeteer

Claude likes to play safe so it called the OpenClaw idea unrealistic

building ideas literally changes people’s lives fr

Access Bulbul V3 at no cost for the rest of the month. The mic is yours! Start building 🚀 dashboard.sarvam.ai/text-to-speech

@hthieblot @LoneMWB @GZinMetaverse @DhruvDiddi @Kevinfromkz @stsqit @astridwilde1 @DevSodhi @hthieblot hey! sent you a dm

@LoneMWB @GZinMetaverse @DhruvDiddi @Kevinfromkz @stsqit @astridwilde1 @DevSodhi Epic

Thanks to the hosts @GZinMetaverse @DhruvDiddi @Kevinfromkz @stsqit @astridwilde1 @DevSodhi @ericmockler

docs are friction for developers i’m building an agent that spins up a real environment, uses your product end to end, tests it, and ships real workflows basically automating fde work

@williamfalcon @kchonyc Sent you an email :)

Coming back to NYU with 2 feet of snow apparently! Excited to chat with @kchonyc on Tuesday Jan 27th in Brooklyn! Perfect for researchers, AI teams, and anyone working on frontier or production AI. Registration: go.lightning.ai/4a8oYHM

@modal Big thanks to @akshat_b for the credits!

You can have your own multi-node training solution: modal run train.py runs the full RLHF pipeline (SFT → Reward Model → PPO) on @modal multi-node H100 cluster. That's literally it. Under $70 for the entire training run. github.com/NilayYadav/mul…