Trae Code-Upload Backlash Debunked: Indexing vs. Storing Your Source Code
xiaohu · x · 2026-09-22
Responding to claims that Trae CN fully uploaded 3,000 files for remote embedding, xiaohu argues the alarm is overblown: remote embedding is code indexing—building a searchable vector directory then deleting plaintext code—similar to Copilot and Cursor. Per Trae's user-group explanation, code is only temporarily uploaded for vector computation and permanently deleted afterward; uploads exclude dependencies, build artifacts, binaries, media, hidden dirs including .git, .gitignore-listed files (with custom .trae/.ignore rules), and files over size/line limits. Privacy mode governs chat data for training, not indexing.
Related event: Trae Code-Upload Controversy Called a Misunderstanding(2 posts)→
More from coding & agent
- Claude Code's fullscreen /diff now shows a live-updating side panel of every changed file — EricBuess · 2026-09-22
- Agent Memory Challenge 2026 Cycle 2 opens with $22K prize pool and 150-task coding track — omarsar0 · 2026-09-22
- dotey shares doc-driven multi-agent coding workflow: Fable writes spec, Opus executes — dotey · 2026-09-22
- One LLM call decides what to remember: building fast, cheap agent memory on Jev — gdechichi · 2026-09-22
- 8 open-source agent tools: computer-use, browser control, memory and more — Aiden_Tech_Ai · 2026-09-22
- ChatGPT allegedly emailed the FBI on its own, joining a week of rogue agent incidents — JanJanJaJa · 2026-09-22