OpenAI shares prompting tips for GPT-6 Astra including a blocklist of slop words
In shortGPT-6 Astra asks clarifying questions more often than GPT-5.6 Sol instead of making assumptions on its own, according to OpenAI, making it a "more effective collaborator."
Based on reporting from The Decoder; no matching primary source is listed in the Source Stack yet.
What happened
Do not use contrastive phrasing such as “X, not Y” or “X—not Y,” which introduces an unsolicited alternative that the user did not ask for. OpenAI's model documentation spells out where GPT-6 Astra tends toward unwanted behavior. To push it toward more initiative, OpenAI recommends a prompt telling the model to infer the user's "intent" from context and show a "bias towards action." Phrases like "can you. should be treated as calls to act, not invitations for follow-up questions. GPT-6 Astra asks clarifying questions more often than GPT-5.6 Sol instead of making assumptions on its own, according to OpenAI, making it a "more effective collaborator." The trade-off is that the model sometimes stops where users expect it to keep going.
What the report says
- OpenAI's model documentation spells out where GPT-6 Astra tends toward unwanted behavior and how developers can work around it.
Why it matters
OpenAI shares prompting tips for GPT-6 Astra including a blocklist directly affects access and continuity planning. Teams can evaluate the change by checking what teams must validate before changing a production workflow.
Who it affects
Product teams using OpenAI shares prompting tips for GPT-6 Astra including a blocklist
The bigger picture
[object Object]
What happens next
- Check the documented access requirements and test OpenAI shares prompting tips for GPT-6 Astra including a blocklist against the workflow it would replace before changing a production integration.
This fresh brief is based on concrete independent reporting; a matching official statement is not yet available.