@Nakarena@karpathy This is something I have been trying to explore. What have you found to work best in your video and diagrams creation workflow? Do you prompt in a specific way or just tell the LLM your goal then it figures out how to do it then iterate?
Google, Anthropic, and OpenAI shared their recipe for Prompting and Agents for free,
if you haven’t read them you’re missing out:
1. Prompting Guide by Google: https://t.co/qUF7C02wgT
2. Building Effective Agents by Anthropic: https://t.co/td8xfSq4wt
3. Prompt Engineering by Anthropic: https://t.co/K7AljEaXtJ
4. A Practical Guide to Building Agents by OpenAI: https://t.co/Gg4dj78wWV
Natural language is the new programming language! 🔥 The way you phrase your prompts matters—clear, precise English leads to better AI-generated responses. Mastering prompt engineering is the key to unlocking AI’s full potential.
Mercury—the first commercial-grade diffusion large language model (dLLM)! dLLMs are revolutionizing AI with parallel, coarse-to-fine text generation, pushing the boundaries of intelligence and speed. Exciting times ahead!
We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the frontier of intelligence and speed with parallel, coarse-to-fine text generation.
Today we’re releasing a research preview of GPT-4.5—our largest and best model for chat yet.
Rolling out now to all ChatGPT Pro users, followed by Plus and Team users next week, then Enterprise and Edu users the following week.
Introducing Claude 3.7 Sonnet: our most intelligent model to date. It's a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking.
One model, two ways to think.
We’re also releasing an agentic coding tool: Claude Code.
We’re launching a free version of Gemini Code Assist globally to help you build faster. It comes with:
🛠️ 180K code completions per month
🌐 Support for all programming languages in the public domain
💡 128K token context window
Get started → https://t.co/pTxUFUEUDG
🚨 Off-Peak Discounts Alert!
Starting today, enjoy off-peak discounts on the DeepSeek API Platform from 16:30–00:30 UTC daily:
🔹 DeepSeek-V3 at 50% off
🔹 DeepSeek-R1 at a massive 75% off
Maximize your resources smarter — save more during these high-value hours!