The Replit Team

Last week, we launched Replit Agent, our AI system that can create and deploy applications. Now, with only a few sentences and a few minutes, you can take an application from idea to deployment.

You can think about the Agent like a pair programmer. It configures your development environment, installs dependencies, and executes code. From your laptop or the Replit mobile app, the Agent is changing how our users build software.

If you'd like to learn more, we've compiled some of our favorite examples, tutorials, and articles on the agent so far. 

Introducing Replit Agent

Amjad Masad

Samip Dahal

Luis Héctor Chávez


Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples -- as little as zero -- to create language wonders. LLMs can chat, write poetry, write code, and even do basic arithmetic. However, the same properties that make LLMs magical also make them challenging from an engineering perspective.

At Replit we have deployed transformer-based language models of all sizes: ~100m parameter models for search and spam, 1-10B models for a code autocomplete product we call GhostWriter, and 100B+ models for features that require a higher reasoning ability. In this post we'll talk about what we've learned about building and hosting large language models.



Nonsense

Any sufficiently advanced bullshit is indistinguishable from intelligence, or so the LLM thought. LLMs are super suggestible -- in fact, the primary way to interact with LLMs is via "prompting." Basically, you give the LLM a string of text and it generates a response, mostly in text form although some models can also generate audio or even images. The problem is, you can prompt the LLM with nonsense and it will generate nonsense. Garbage in, garbage out. Also, LLMs tend to get stuck in loops, repeating the same thing over and over again, since they have a limited attention span when dealing with some novel scenarios that were not present during training.

Productizing Large Language Models

Alexandre Cai 

Giuseppe Burtini

Update: Ghostwriter is out now!

In 2018 when we announced Multiplayer Mode, we said it's the most significant evolution of Replit to date. For the first time, you could share a URL with a friend, student, or coworker and get a shared text editor and runtime — no setup required. Replit Multiplayer is changing how an entire generation of programmers learn how to code and make software.

Today, we're announcing Ghostwriter, which infuses state-of-the-art intelligence into nearly all IDE features. Ghostwriter sports an ML-powered pair programmer that completes your code in realtime, tools to generate, transform, and explain code, and an in-editor search utility that lets you find and import open-source code without leaving your editor (think Stackoverflow in your editor).



Introducing Replit Agent

Productizing Large Language Models

Ghostwriter AI & Complete Code Beta