# How We Developed Zeta2

DevFeed: [How We Developed Zeta2](<https://devfeed.tech/articles/how-we-developed-zeta2-13500.md>)

Original publisher: [Read original article](<https://zed.dev/blog/how-we-developed-zeta2>)

Author: Oleksiy Syvokon, Ben Kunkle

Published: 2026-04-07T00:00:00Z

Content type: article

Language: en

Sources: [Zed Industries - Blog](<https://devfeed.tech/sources/zed-industries-blog.md>)

Topics: [Development](<https://devfeed.tech/topics/development.md>), [Code](<https://devfeed.tech/topics/code.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Testing](<https://devfeed.tech/topics/testing.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [development](<https://devfeed.tech/tags/development.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [examples](<https://devfeed.tech/tags/examples.md>), [github](<https://devfeed.tech/tags/github.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [testing](<https://devfeed.tech/tags/testing.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

Zed describes how it developed Zeta2, a faster edit-prediction model trained through knowledge distillation. The process used richer code context, ethically collected starting states, teacher-prompt evaluation, and roughly 100,000 synthetic examples derived from GitHub commits.

## Source excerpt

A deep dive into how we improved our Zeta edit predictions model, Zeta2.