Card #323 · OpenAI Platform & APIs
Simple prompts flagged as policy violations in Playground for o1 and o3
Even basic prompts like "hi" or "Hello" are being incorrectly flagged as violating usage policy when using o1 and o3 models in the OpenAI Playground. This issue does not occur with the gpt-4o model and is causing significant disruptions to development work.
Pain score
0.18/ 1.00 · weighted product of four components
Reach0.32distinct authors (log-normalized)
Recency1.00freshness decay, half-life months
Engagement1.00upvotes + comments, normalized
Monetization1.00willingness-to-pay cues in evidence
§ Evidence — 3 verified quotes
even simple prompts like “Hello” are flagged as violating usage policy
I realized that even a simple “hi” would lead to the same problem
It’s causing significant disruptions to my work, and the lack of response is unacceptable.
Comments are a Pro feature — join the conversation, share what you've shipped, hear what others are building.
Upgrade to Pro