
give me this and an LLM
Manas Vaze
6.3K posts

@manasvaze
Currently: Design Lead @realfastai prev: @teamsundial @olacabs @swiggy

give me this and an LLM

Developers: Join us on May 13. A first look at our new developer platform. Let's build, together. ntn.so/developers

For anyone who used a computer between 1990 & 2005… what’s the one game you still think about?

I built a Chrome extension that helps you extract styles from any website and generate DESIGN(.)md or SKILL(.)md files Works with Google Stitch, Claude Code, Codex etc ... and it's free!



VARUN DHAWAN - MRUNAL THAKUR - POOJA HEGDE: 'HAI JAWANI TOH ISHQ HONA HAI' FIRST LOOK UNVEILED – 22 MAY 2026 RELEASE... Here's the first look of the feel-good, massy entertainer #HaiJawaniTohIshqHonaHai, starring #VarunDhawan, #MrunalThakur, and #PoojaHegde. 🔗: bit.ly/HJTIHH_FirstLo… This marks the 46th directorial venture of David Dhawan, who reunites with producer Ramesh Taurani [Tips Films] for #HJTIHH, set to arrive in cinemas on 22 May 2026. Co-produced by Maximilian Films [UK].


In 452 AD, Pope Leo I met with Attila the Hun near Mantua, Italy, and successfully persuaded him to halt his invasion of Rome. Prayers for Leo XIV 🙏


Advice to fellow side project tinkerers: don't forget to set up aggressive logging! (OTel traces + manual event capture + Vercel log drain into Axiom works great for me) I can fix most bug reports by pasting the user's email into an LLM connected to the Axiom MCP. Between events and traces, the model can replay nearly any timeline of activity and figure things out with a high level of detail. Don't forget to scrub PII. Over-log at first and trim back as you build confidence in different areas of the code. MCPs are still fine, ignore the haters. This works fine at a small scale, ofc.




Introducing CSS Studio. A design tool that lives in your site. Runs in your browser. Writes code with your existing AI agent. All completely local - so no subscription. One price, lifetime updates.