Engineering Insights

Introducing SWE-bench Verified

We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.

Introduction to ggml

Zero downtime migrations at petabyte scale

Scaling challenges, frequent maintenance tasks, constant fear of when it's going to all fall over, and quickly rising costs — these are all common issues that teams will put up with just to avoid the task of migrating a database that has outgrown its home. And with good reason. There is a lot of risk in moving from one database server or system to another: extended downtime, data loss, version incompatibilities, and errors no one could have even predicted. But what if I told you it doesn't have

How to build scalable AI applications

In today's AI-driven landscape, your business's competitive edge lies in how effectively you integrate AI into your product and workflows. This guide focuses on three critical aspects of building scalable AI applications: Read more

Welcome Falcon Mamba: The first strong attention-free 7B model

Tool Use, Unified

Update regarding Vercel service disruption on August 7, 2024

On August 7, 2024, Vercel's Edge Middleware and Edge Functions experienced a significant outage affecting many customers. We sincerely apologize for the service disruption. Vercel’s platform is designed to . As standard practice, we use staggered rollouts for both code and configuration changes. Every aspect of our infrastructure is designed to gracefully fail over to the next available region in the event of an incident, and ensures no single point of failure across infrastructure components. H

Gotta cache 'em all: bending the rules of web cache exploitation

Through the years, we have seen many attacks exploiting web caches to hijack sensitive information or store malicious payloads. However, as CDNs became more popular, new discrepancies between propriet