“Any time a programmer makes a decision about how to deal with data, how to average it or clean it, you’re imparting more of your own bias on it.” — Hannah Fry
What tasks should AI be trusted with, and when should humans remain involved? Designing those decision rights is one of the defining challenges of the AI era. Researchers at the MIT Center for Information Systems Research have developed a framework to help.
Learn more: https://t.co/NbTi0Vvd7Z
To build my agent I used python. Its purpose is to reads, links and take notes for me. It runs in docker on a $ droplet, and only reachable over tailscale. I denied it access to sensitive information like private, family, passwords, and finance folders. They are hard off-limits.
learning a ton.
AI agents let you connect LLMs to real-world workflows.
In this course, @ania_kubow shows you how to build and deploy an AI-powered Slackbot.
You'll use Node.js, Express, Slack Bolt, GPT-4, PostgreSQL, and Render to research and get new community members.
https://t.co/90tEck3YXU
@OpenRouter it's good to see a chart that shows the full graph instead of part of it. also, 23 of the 36 banchmarks averaging 83.5 latency accuracy for a model to make decisions is good. with a 64 percent passing rate, to me 23 of 36 seem like the model is inconsistent.