Grok Build Offers Stronger Privacy Controls Than Codex
XFreeze · x · 2026-07-16
Grok Build is described as prioritizing privacy much more than Codex:
- Data retention is disabled by default, and a /privacy command is provided to delete previously synced data.
- All previously retained coding data has been completely purged.
- The entire harness can be run locally with your own inference models, allowing for line-by-line auditing.
The post also criticizes OpenAI Codex (ChatGPT Plus/Pro) for defaulting to train models on user conversations and code. Turning off data usage requires manually navigating to the settings/privacy page, chat history is retained for about 30 days, and true, comprehensive privacy controls are locked behind the Enterprise tier.
More from coding & agent
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11