Raw footage of Devin! Expect to see more soon 👀

I've been playing around with Cognition' Devin on and off today. It's so cool.

Little things, like a site with top 20 restaurants in Brooklyn using a scoring algorithm it designed.

Two things that will become more valuable in a post-Devin world:

- Imagination
- API Keys

The hottest new programming language is English 😀

Solving >10% of our SWE-Bench (swebench.com) is THE most impressive result in 2024 so far, and a milestone for the research and application of AI agents. Congrats Cognition !

Devin iteratively making a Game of Life website!

Play the game: curious-choux-109a4b.netlify.app

Read more on our blog: cognition-labs.com/blog

It's wonderful seeing Devin helping people build projects already!

These aren't just cherrypicked demos. Devin is, in my experience, very impressive in practice.

Devin is 𝘪𝘯𝘤𝘳𝘦𝘥𝘪𝘣𝘭𝘦 at data extraction. Over the past few weeks, I've been scraping data from different blogs and Devin

1. writes the scraper to navigate the website
2. executes the code
3. returns a labeled CSV file

Devin is a multi-step agent that actually works 🤯

This is the first AI agent I've used that feels like a real, useful person is on the other end.

Getting status updates like 'Looking in the docs for how to set up the Docker container' and 'Fixing an issue with connecting to the database,' plus having visibility on what Devin is…

First time I have seen an AI take a complex task, break it down into steps, complete it, and show a human every step along the way - to a point where it can fully take a task off a human's plate. All built in just a few months. Excited to see where Scott Wu Walden Neal Wu…

This is the first demo of any agent, leave alone coding, that seems to cross the threshold of what is human level and works reliably. It also tells us what is possible by combining LLMs and tree search algorithms: you want systems that can try plans, look at results, replan, and…