suraj kumar

INSTEAD OF WATCHING CLAUDE CODE WORK. An Anthropic engineer built a setup that ships features while you sleep. 22 minutes. Free. Watch it, then copy the exact workflow.

@Ronycoder A better use of 32 minutes, for sure.

INSTEAD OF WATCHING AN HOUR OF NETFIX TONIGHT. This 32-min Stanford lecture by Graham Weaver will teach you more about living boldly than 10 years of self-help books. Bookmark it and give it 32 minutes, no matter what.

INSTEAD OF WATCHING CLAUDE CODE WORK. An Anthropic engineer built a setup that ships features while you sleep. 22 minutes. Free. Watch it, then copy the exact workflow.

I made $14,200 last month using Claude, a laptop, and just 60 minutes a day. No clients chasing. No team. No burnout. I broke down the exact process into a simple step-by-step guide. It used to be $129. Right now → it’s FREE for few hours. Like + comment “GUIDE” and I’ll send you the full playbook. Must follow to receive the DM. ⏳ Available for a limited time.

@Alokkumarzz Guide

Best accounts to follow from each frontier lab to stay constantly up to date Anthropic @karpathy - must-follow account for AI; recently joined Anthropic @bcherny - Claude Code creator, always shares great tips @trq212 - also a Claude Code developer; writes amazing articles on CC OpenAI @polynoamial - works on reasoning research, shares a lot of technical details @gabriel1 - Sora developer, great career path @jxnlco - works on dev experience, shares a lot about Codex Google AI @OfficialLoganK - all the major Google Gemini and AI Studio updates @ammaar - product and design; shares great things about vibe-coding in Google AI Studio @fofrAI - cool use cases for generative models Cursor @leerob - the loudest voice behind Cursor updates @ericzakariasson - shares great insights on using Cursor @mntruell - Cursor’s CEO; major releases and usage updates xAI @milichab - recently joined xAI, shares updates on Grok @skcd42 - also covers major Grok releases @ai_explorer25 - covers all ai content and free resources

How to get smart....

Seedance 2.0 = 550+ UGC Ads/Day Realistic AI-generated UGC ads with natural movement and premium quality. Around $1 per ad Created in minutes Scale as much as you want My workflow automatically creates, tests, and scales ads 24/7. Want the full setup? Comment "UGC" 👇

@peter11n Glad you found helpful!

@Surajcoder Thanks for sharing.

@Alokkumarzz THANKS!

@Surajcoder Definately watching this!

【Warning】 If you're using Gemini, check these settings right now. If they're still set to the defaults, your Gmail and Google Drive data may be accessible to Gemini. If you haven't changed these settings yet, consider doing so immediately.

BREAKING 🚨 ATTENTION GEMINI USERS! CHECK THIS IMMEDIATELY! IF YOU'RE USING THE DEFAULT SETTINGS, YOUR GMAIL AND GOOGLE DRIVE CONTENTS ARE COMPLETELY VISIBLE. IF YOU'RE USING THE DEFAULT SETTINGS, CHANGE THEM NOW! ↓

@HeyRohhit Definitely worth an hour of your time.

Instead of watching an hour of Netflix, watch this 60 minute lecture from Steve Jobs after being fired from Apple. It will teach you more about building companies than most startup books ever will.

@TechByMarkandey The feedback loop is usually the missing piece, not the model itself.

Everyone wants better AI agents. The challenge isn't collecting more data. It's making sense of the massive amount of production traffic, traces, tool calls, and feedback agents generate every day. That's why Adaline is interesting. It turns production behavior into evals by identifying patterns, surfacing failures and drift, generating synthetic scenarios based on real usage, and continuously creating new tests to improve agent performance. What stood out is that humans stay in control. Adaline can build agent candidates from what it learns, but a human reviews and approves changes before anything goes live. The next leap in AI agents may come less from bigger models and more from better feedback loops.

@Ronycoder This feels like a more meaningful direction.

i don't think the next breakthrough in agents is a bigger model. it's giving agents a way to learn from their own production mistakes. reading traces, identifying recurring behaviors, generating evals, and improving from real-world usage feels like a much more important direction than most people realize. this is basically that, shipped.

@Alokkumarzz Great thread! Most people use WhatsApp daily but rarely explore features that can improve privacy and productivity.

WhatsApp has more than 1.9 billion users worldwide. But 97% of people don’t know its true potential. Here are 15 essential tricks you should know: