v1.4.1 — Multi-AI Code Review + The Brain Dreams #12
wazionapps
announced in
Announcements
Replies: 1 comment
-
|
For anyone curious about the multi-AI review process: we gave GPT-5.4 (Codex), Gemini 2.5, and Claude Opus full read access to the codebase simultaneously. Each reviewed independently, then we synthesized their findings. The three bugs they caught were all silent failures — the kind that pass tests but fail in production. Worth trying on your own projects. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
What is new
This release was unique: we gave GPT-5.4 (Codex CLI) and Gemini 2.5 (Gemini CLI) full access to the NEXO codebase and asked them to review it alongside Claude Opus.
Bugs Fixed
Security
Memory sanitization prevents prompt injection via stored content.
The Brain Dreams (v1.4.0)
All 9 nightly scripts migrated from Python word-matching to Claude CLI (opus). The brain uses its own intelligence to consolidate memories during sleep.
Full notes: https://github.com/wazionapps/nexo/releases/tag/v1.4.1
Beta Was this translation helpful? Give feedback.
All reactions