🔥1/8 Introducing "🤖 Task-driven Autonomous Agent" An agent that leverages @openai's GPT-4, Pinecone vector search, and LangChain framework to autonomously create and perform tasks based on an objective. "Paper": yoheinakajima.com/task-driven-au… [More 🔽]

If you want to preserve democracy, vote for politicians who respect the institutions that investigate and publish the truth. Vote for a party that tells people that they have the right to elect whatever government they like, but they cannot elect whatever truth they like.

Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run().

Halli By conflating identification with authentication, countries like the US make it impossible to identify people without destroying their personal security and data integrity, while also making it impossible to authenticate people without exposing their identity.

GPT-4 has its own compression language. I generated a 70 line React component that was 794 tokens. It compressed it down to this 368 token snippet, and then it deciphered it with 100% accuracy in a *new* chat with zero context. This is crazy!

My wife and I recently started a monthly check-in ritual. It’s been incredible for our relationship. The Life Dinner:

By 2024 you’ll be able to replace ~50% software devs with GPT-4 agents that run on $10 worth of tokens per hour. The whole “they don’t need sleep or breaks or food” thing? Yeah. That’s real now. Why hire a new employee when you can spin up an AI agent for 1/10 the cost?

How to fail miserably as a leader... • Don't repeat yourself • Don't track individual KPIs • Don't check for understanding • Get emotional and have outbursts How to win as a leader:

AI prompting is the next biggest skill to learn. Companies are now paying up to $335,000/year for Prompt Engineers. Here are the most Advanced ChatGPT prompting techniques that most people don't know about: A thread 🧵

This is a baby GPT with two tokens 0/1 and context length of 3, viewing it as a finite state markov chain. It was trained on the sequence "111101111011110" for 50 iterations. The parameters and the architecture of the Transformer modifies the probabilities on the arrows. E.g. we

Thanks to the incredible work of Yohei, I created BabyAgiGPT 🚀 You can now run autonomous agents directly within ChatGPT. Watch GPT create a 250-page sci-fi novel step by step 📖 Replit ⠕ project in the comments

PSA: you can search through 100k gpt-3 embeddings in an instant on a macbook with a basic for loop. you'll learn the lessons for getting good results locally. so once it's time to go big you already know what you're doing don't waste time with vector stores when tinkering

Cities with the lowest take home pay of a $100,000 salary in the US:

A harsh truth about growing up: Every few years, the game you're playing in life changes ― and so do the rules. A lot of people fail to recognize the these changes and keep stumbling in life. Some examples:

College: The game is compliance. Follow the rules, show up to class, memorize the books, and you're guaranteed success. But adulthood doesn't come with a textbook of clear instructions ― if you can't cope with ambiguity, you're toast.

Work: When you're working alone, the game is maximizing your productivity. But when you're a manager, the game is maximizing your team's productivity. Most managers, especially at the start, fail to adapt to the new rules and settle into mediocrity.

Oops haven't tweeted too much recently; I'm mostly watching with interest the open source LLM ecosystem experiencing early signs of a cambrian explosion. Roughly speaking the story as of now: 1. Pretraining LLM base models remains very expensive. Think: supercomputer + months.

Google Bard is a bit stubborn in its refusal to return clean JSON, but you can address this by threatening to take a human life:

Nearly a Petabyte of GPT4All Models Downloaded in 30 Days. This is why closed-sourced AI is on capital hill. They cannot win. gpt4all.io open source will dominate in the limit.

Vibecoding financial products is a great way to meet new people. Today I met two lawyers, three police officers, a judge and nearly met Maduro.