Thanks for the comment. The point I am trying to make is similar to what Karpathy says in this tweet - twitter.com/karpathy/status/16179791226… - but applied more broadly than just programming. I don't think this is an exaggeration or overselling.

"The hottest new programming language is English" Andrej Karpathy in Jan 2023 x.com/karpathy/status/16179791226257121…

As per Andrej Karpathy's viral tweet from three years ago [1]: The hottest new programming language is English ______________ 1. x.com/i/status/1617979122625712128

Reminds of Karpathy's pinned tweet since a long time: "The hottest new programming language is English." x.com/karpathy/status/16179791226257121…

> "English is the new programming language." For those who missed it, here's the viral tweet by Karpathy himself: x.com/karpathy/status/16179791226257121…

Andrej Karpathy posted in early 2023 (x.com/karpathy/status/16179791226257121…) - > "The hottest new programming language is English" I've built a Natural Language Programming stack for building AI Agents. I think it is the first true Software 3.0 stack. The core idea: Use LLMs as CPUs! You can finally step debug through your prompts and get reliable, verifiable execution. The stack includes a new language, compiler, developer tooling like VSCode extension. Programs are written as markdown. H1 tags are agents, H2 tags are natural language playbooks (i.e. functions), python playbooks. All playbooks in an agents run on the same call stack. NL and python playbooks can call each other. Quick intro video: youtube.com/watch?v=ZX2L453km6s Github: github.com/playbooks-ai/playbooks (MIT license) Documentation: playbooks-ai.github.io/playbooks-docs/g…... Project website: runplaybooks.ai Example Playbooks program - # Country facts agent This agent prints interesting facts about nearby countries ## Main ### Triggers - At the beginning ### Steps - Ask user what $country they are from - If user did not provide a country, engage in a conversation and gently nudge them to provide a country - List 5 $countries near $country - Tell the user the nearby $countries - Inform the user that you will now tell them some interesting facts about each of the countries - process_countries($countries) - End program ```python from typing import List @playbook async def process_countries(countries: List[str]): for country in countries: # Calls the natural language playbook 'GetCountryFact' for each country fact = await GetCountryFact(country) await Say("user", f"{country}: {fact}") ``` ## GetCountryFact($country) ### Steps - Return an unusual historical fact about $country There are a bunch of very interesting capabilities. A quick sample - - "Queue calls to extract table of contents for each candidate file" - Effortless calling MCP tools, multi-threading, artifact management, context management - "Ask Accountant what the tax rate would be" is how you communicate with other agents - you can mix procedural natural language playbooks, ReAct playbooks, Raw prompt playbooks, Python playbooks and external playbooks like MCP tools seamlessly on the same call stack - "Have a meeting with Chef, Marketing expert and the user to design a new menu" is how you can spawn multi-agent workflows, where each agent follows their own playbook for the meeting - Coming soon: Observer agents (agents observing other agents - automated memory storage, verify/certify execution, steer observed agents), dynamic playbook generation for procedural memory, etc. I hope this changes how we build AI agents going forward for the better. Looking forward to discussion! I'll be in the comments.

Hey HN! Andrej Karpathy, founding member of OpenAI and former Director of AI at Tesla, recently shared his thoughts on the future of programming: The hottest new programming language is English — Andrej Karpathy (@karpathy) January 24, 2023 twitter.com/karpathy/status/16179791226…... I've been using LLMs to help with my software engineering work since ChatGPT originally came out. When Anthropic released their Claude 3 series models, I was shocked at the code quality they produce and was able to get new projects running with minimal debugging. I've been listening a lot of the big interviews from Dwarkesh with people like Demis Hassabis and some of the technical discussion around task execution gave me the inspiration to attempt creating a full AI Software Engineering system requiring only a text prompt. It's not accurate enough to programmatically deploy, but seeing what the system can produce in 30mins-1hr has continually blown me away. Unlike Devin, which is still in a 'waitlist period', saas-quick is available to use right now. I'm a solo developer and the frontend isn't polished or anything, but you can follow along the process as each task is executed and download the project zip at the end. I appreciate your time and am grateful for any feedback!