code-completion edit-prediction zed-editor model-scaling lsp

Zeta2 edit prediction model reaches 30% acceptance improvement

Zed's Zeta2 scales from 500 hand-curated training examples to 100,000 opt-in collected samples, replacing context-blind predictions with LSP-based symbol resolution.

July 9, 2026

Summary

Edit prediction accuracy directly affects keystroke savings in your primary workflow. Zeta2's LSP context integration eliminates guessing on cross-module dependencies, reducing dismiss-and-retype cycles.

Why it matters

Implementation verdict

Drop-in replacement for Zeta1 (already default in Zed). Requires no configuration; LSP context shipped in 0.222.2+. Worth enabling now if you use Zed—no switching cost. Consider opting into training data collection if you work in open-source repos to help close the gap with larger models.

Sources

1.acceptance rate is 30% better than Zeta1
2.trained on nearly 100,000 examples collected on an opt-in basis
3.Zeta1 was trained on a hand-curated set of around 500 examples
4.Zeta2 is trained entirely on open source code
5.LSP-based context retrieval (the same infrastructure that powers go-to-definition)

Dev Signal

Get briefs like this in your inbox — free, every weekday.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.

Read the full issue →All briefs