Intel / post

Kilo Code ships whole-file Next-Edit on Mercury Edit 2

Source: x.com
Date: Published Jun 29, 2026

Inception@_inception_ai

Next-Edit just shipped in @kilocode, powered by Mercury Edit 2, our diffusion LLM. It predicts your next change anywhere in the file, not just the tokens ahead of your cursor. Diffusion means the edit comes back fast enough to stay in flow. Tab to accept. Free for everyone through July 23, no key required. https://t.co/DiWzfaCzxJ

Jun 29, 2026 View on X

Context

Kilo's Next-Edit feature uses recent changes and file to suggest another edit elsewhere in the same file. Powered by Inception's Mercury Edit 2, it extends assistance beyond completing text at the cursor: a suggestion can target a related rename or modification in another location, with Tab used to accept it. Kilo retained conventional autocomplete as a separate option. Its launch promotion covered use through the Kilo Gateway until July 23, 2026, so the announcement's free-access offer had a defined end date.

Terms in this piece · Glossary

context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.

Read the source x.com