Engineering Insights

Improving language model behavior by training on a curated dataset

Our latest research finds we can improve language model behavior with respect to specific behavioral values by fine-tuning on a small, curated dataset.

Poppy adopted Prisma 2 in its early days and has seen enormous benefits from the type safety that Prisma Client provides.

Poppy offers rides of all kinds through its mobile app. Whether it's a car, scooter, or e-step, Poppy has it. Prisma plays a vital role in helping Poppy ship quickly and confidently and is a big reason they've just hit 1.5 million total rides taken.

The Plan for React 18

The React team is excited to share a few updates. We’ve started work on the React 18 release, which will be our next major version. We’ve created a Working Group to prepare the community for gradual adoption of new features in React 18. We’ve published a React 18 Alpha so that library authors can try it and provide feedback...

Node.js 16.3.0 (Current)

Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API

Announcing the Prisma Ambassador Program — Building A Community of Experts

We are thrilled to announce the launch of the Ambassador Program to empower the Prisma community, while also helping individual contributors build their own brand.

Using & Mixing Hugging Face Models with Gradio 2.0

Serverless finally has a database

In 2010, when the Vitess project was started to help the YouTube team at Google handle MySQL database scalability issues, the Ruby on Rails application framework was about 5 years old, and there were already several “Unicorn” companies that had leveraged both technologies to massive success. What has happened in the interim? If you trace the advancements in databases, do they compare with the advancements in application development? More than 10 years later, Rails has gone on to be tremendously