OpenAI appears to be silently re-enabling model training on Codex chats
user052919 · hn · 2026-11-03
An HN user reports that their company, which diligently disables data sharing in Codex/Claude Code to avoid leaking IP to frontier labs, found the "Improve the model for everyone" setting silently re-enabled in Codex without anyone opting back in.
They link to where users can check and disable it (chatgpt.com/settings/data-controls and privacy.openai.com/policies?modal=take-control), note a prior HN thread spotted the same issue, and ask whether it's isolated or widespread. Enterprise users concerned about code privacy should verify their settings.
More from Safety
- ARTEX red team tool's Docker image found to contain an unauthorized backdoor — Kyrannio · 2026-11-04
- India's CERT-In gets Anthropic's Claude 'Mythos' to probe cybersecurity flaws, skeptics unimpressed — kingslyj · 2026-11-04
- Ternary Logic proposal: enforcing AI safety at the architecture level — MoralLogs · 2026-11-04
- Cambridge's David Krueger: A global AI pause needs coordination, not trust — DavidSKrueger · 2026-11-04
- Security advisory: run AI agents in managed cloud environments, not employee endpoints — amasad · 2026-11-04
- Man who siphoned 4M accounts' credits from AI platform reselling them gets suspended sentence — 葬AI · 2026-11-04