Block4Roots (@Block4Roots) header
Block4Roots (@Block4Roots) profile picture

20% jokes, 80% alpha. Building an AI team that does real outreach. Ex CM @gatedesi building Block4roots

Joined December 2022
Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)Photo by Block4Roots (@Block4Roots)
There are thousands of AI tools. You need maybe 3. So I built a map: pick your job, get the best tool, the best free one, and the easiest one to start with. 114 tools. 12 jobs. English + Hindi. Find yours in under a minute 👇
2
3
11
414
Context window = the AI's working memory. It's how much text the model can see at once: your prompt, files and its reply. Bigger isn't automatically better. As it fills up, accuracy drops. Long chat going weird? Start a fresh one with a short summary.
8
Canva vs Adobe Express for quick social posts: which one and why? Both have free plans and AI features. I want to know what you actually open when a post is due in 10 minutes.
1
44
New to Jio? The free Google AI Pro offer is gone. It ended on 29 Oct. New recharges don't include it, and Jio now bundles 12 months of Canva Pro instead. Already have it? You keep access as long as you stay on an unlimited 5G plan of ₹349 or more. Check before you downgrade.
96
5 free guides to AI agents worth saving. For beginners who keep hearing "agents" and want to build one. 1. AI Agents Course: Hugging Face, step by step huggingface.co/learn/agents-… 2. Building effective agents: Anthropic on when to use agents and when not to anthropic.com/engineering/bu… 3. AI Agents for Beginners: Microsoft's 18 lessons on GitHub github.com/microsoft/ai-agen… 4. A practical guide to building agents: OpenAI's free PDF cdn.openai.com/business-guid… 5. ADK docs: Google's open-source framework for building agents google.github.io/adk-docs/
2
40
Before you ask AI to build something, write down how you'll check it worked. Build the check first, then let the agent code until it passes. That's the shift developers keep talking about.
5
165
Block4Roots retweeted
Google is making a big move with Gemini. It's no longer just about asking AI questions. It's about handing AI actual responsibilities. Sundar Pichai just announced Gemini Tasks, bringing agentic capabilities to hundreds of millions of users across 6 countries, free of charge. Here's what caught my attention: 1. Email to action Forward an email to Gemini and it can RSVP and add the event to your family calendar. 2. AI that makes phone calls Ask Gemini to contact local businesses, compare prices and check product availability. You get call transcripts and approval before dialing. 3. Payments Gemini can securely check out using Google Pay, powered by the Agent Payments Protocol (AP2). 4. Account access Google Password Manager helps agents sign in without making users manually handle every step. 5. Global rollout Tasks is rolling out across the US, India, Japan, South Korea, Canada and Australia. Advanced actions like calling, texting and payments are starting in the US. My take: The interesting part isn't another AI model getting smarter. It's Google connecting AI to the services people already use. Think about the time spent calling shops, comparing prices, managing emails, booking things and handling small daily tasks. If AI can reliably take care of these jobs, it becomes much more valuable than a chatbot. But there's one big challenge: Giving AI access is easy. Earning enough trust to let it act on your behalf is the real battle. We're getting closer to AI that doesn't just tell us what to do. It actually does it.
Knowing things → doing things → finding ways to save you time and money We’re expanding Tasks in Gemini free of charge to hundreds of millions of people in six countries. Powered by Gemini 4 Hydrogen, Tasks lets you hand off everyday life admin directly: - Forward emails to [email protected] to RSVP and add it to your family calendar - Have Gemini call local businesses to compare price quotes and check inventory (with full transcripts + approval before dialing) - Check out securely via Google Pay (uses the Agent Payments Protocol - AP2) - Seamlessly sign in via Google Password Manager We wanted to make this helpful + secure, we’re also partnering directly with major websites and security providers so it works well for site owners and agents.
1
1
1
5
232
Google is making a big move with Gemini. It's no longer just about asking AI questions. It's about handing AI actual responsibilities. Sundar Pichai just announced Gemini Tasks, bringing agentic capabilities to hundreds of millions of users across 6 countries, free of charge. Here's what caught my attention: 1. Email to action Forward an email to Gemini and it can RSVP and add the event to your family calendar. 2. AI that makes phone calls Ask Gemini to contact local businesses, compare prices and check product availability. You get call transcripts and approval before dialing. 3. Payments Gemini can securely check out using Google Pay, powered by the Agent Payments Protocol (AP2). 4. Account access Google Password Manager helps agents sign in without making users manually handle every step. 5. Global rollout Tasks is rolling out across the US, India, Japan, South Korea, Canada and Australia. Advanced actions like calling, texting and payments are starting in the US. My take: The interesting part isn't another AI model getting smarter. It's Google connecting AI to the services people already use. Think about the time spent calling shops, comparing prices, managing emails, booking things and handling small daily tasks. If AI can reliably take care of these jobs, it becomes much more valuable than a chatbot. But there's one big challenge: Giving AI access is easy. Earning enough trust to let it act on your behalf is the real battle. We're getting closer to AI that doesn't just tell us what to do. It actually does it.
Knowing things → doing things → finding ways to save you time and money We’re expanding Tasks in Gemini free of charge to hundreds of millions of people in six countries. Powered by Gemini 4 Hydrogen, Tasks lets you hand off everyday life admin directly: - Forward emails to [email protected] to RSVP and add it to your family calendar - Have Gemini call local businesses to compare price quotes and check inventory (with full transcripts + approval before dialing) - Check out securely via Google Pay (uses the Agent Payments Protocol - AP2) - Seamlessly sign in via Google Password Manager We wanted to make this helpful + secure, we’re also partnering directly with major websites and security providers so it works well for site owners and agents.
1
1
1
5
232
Block4Roots retweeted
Jensen Huang built NVIDIA from the ground up in 1993. • Started with a vision to transform computer graphics. • Survived near failure and years of uncertainty. • Took a massive bet on GPUs and AI when few understood their potential. • Built CUDA and turned NVIDIA into the backbone of the AI revolution. • Created a company that became one of the most important players in modern technology. And now, 33 years of building are overshadowed by his personal mistakes. He deserves accountability for his actions, but his contribution to technology shouldn't be erased because of them. Leadership is human. So is failure. Both deserve perspective.
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen
1
1
1
6
175
Jensen Huang built NVIDIA from the ground up in 1993. • Started with a vision to transform computer graphics. • Survived near failure and years of uncertainty. • Took a massive bet on GPUs and AI when few understood their potential. • Built CUDA and turned NVIDIA into the backbone of the AI revolution. • Created a company that became one of the most important players in modern technology. And now, 33 years of building are overshadowed by his personal mistakes. He deserves accountability for his actions, but his contribution to technology shouldn't be erased because of them. Leadership is human. So is failure. Both deserve perspective.
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen
1
1
1
6
175
MCP in one line: a USB-C port for AI apps. It's an open-source standard that lets apps like Claude or ChatGPT connect to your files, tools and other apps in one standard way. See "MCP support" on a tool? Your AI assistant can plug into it. modelcontextprotocol.io/
2
34
Block4Roots retweeted
n8n vs Zapier for your first automation: which one and why? Zapier's free plan: 100 tasks a month, nothing to set up. n8n: the Community edition is free when you host it yourself. Zero setup vs your own server.
5
1
11
196
5 free AI courses worth saving. For anyone starting from zero who wants the basics without paying. 1. Elements of AI: University of Helsinki's intro for non-experts elementsofai.com/ 2. Generative AI for Beginners: Microsoft's 21 lessons on GitHub github.com/microsoft/generat… 3. ChatGPT Prompt Engineering for Developers: 1h40m with Andrew Ng and Isa Fulford deeplearning.ai/short-course… 4. Machine Learning Crash Course: Google's videos plus hands-on exercises developers.google.com/machin… 5. LLM Course: Hugging Face's course on how language models work huggingface.co/learn/llm-cou…
1
3
92
n8n vs Zapier for your first automation: which one and why? Zapier's free plan: 100 tasks a month, nothing to set up. n8n: the Community edition is free when you host it yourself. Zero setup vs your own server.
5
1
11
196
Stop telling your AI coding agent to do it "quick" or "just for now". Lauren from the React compiler team pointed out that words like these teach agents to repeat half-fixes across the project. Ask for the root cause and a way to check the fix instead.
3
1
4
101
What's the "thinking" setting in an AI model? Some models, like Google's Gemini 4 Carbon, let you pick low, medium or high thinking. Low: faster replies. High: the model reasons longer before answering, which helps with math, code and tricky tasks. Simple rule: low for quick questions, high when a wrong answer would cost you.
3
82
Grok vs ChatGPT for quick answers on your phone: which one and why? ChatGPT still leads web visits, 56.6% in October. People who pick Grok say it's for speed.
1
19
AI can write the code. It still can't remember why your system was set up that way three years ago.
1
20
People are now adding typos on purpose so their writing doesn't look AI-made. Zara's post about it crossed 100,000 likes. Better fix than typos: add one detail only you could know. A name, a number from your own work, a place.
2
2
4
138
OpenAI's new ChatGPT Wallet lets its AI agents, called "dots", finish online purchases for you. You review the items, price and card, then approve with Face ID or fingerprint. Your real card number stays hidden behind one-time tokens. US Pro users only for now. But the rule is worth copying for any agent you set up: it can prepare everything, and money moves only after you tap yes.
1
2
4
160