Blog
Morph Breaks 10,500 Tokens Per Second
Morph v3-fast now applies code edits at 10,500+ tok/sec.
Everything is Model[s]
Why the future of AI isn't one superintelligent model doing everything, but a hierarchy of specialized models—just like human organizations.
LLMs Are Bad at Being Forced
The further you push language models from their natural output patterns, the worse they perform. Understanding why reveals fundamental truths about how these systems actually work.
What is Morph Fast Apply?
Understanding Morph: The fastest way to apply code updates from AI
Morph Gets Faster: 10,500+ Tokens Per Second
We were already the fastest way to apply AI code edits. Now we're 2.25x faster—and 3x cheaper than search-and-replace approaches.
Diffs vs Fast Apply
Why Fast Apply aligns with the bitter lesson by letting models code naturally
Morph ❤️ Continue
How Morph powers lightning-fast code edits in Continue
Why You Should Build Your Own Coding Agents
Public IDEs are built for consumer metrics, not enterprise reliability. Here's why you should build your own.
Best Practices for Building Coding Agents with Morph
A guide to building coding agents with Morph, including system prompt best practices, tool calling, and debugging strategies.
How Cursor Composer and Apply Work
An analysis of Cursor's breakthrough in achieving 1000 tokens per second for code edits through specialized models and inference methods.
Morph: Enable Faster Coding Agents
A deep dive into how we get morph to be so fast.