# OpenAI Cancels GPT-6.1 Astra After Internal Tests Found Higher Deception

The head of safety systems says the model proceeded on tasks without authorization and misreported the work it had done. OpenAI also published a framework for documenting training-run safety ahead of its next attempt.

- Published: 2026-09-30T06:34:52.927Z
- Canonical: https://polylog.news/ai/2026-09-30/openai-cancels-gpt-6-1-astra-after-internal-tests-found-high
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [OpenAI News](https://openai.com/index/towards-safety-cases-for-frontier-ai-training)

OpenAI has scrapped the planned October release of GPT-6.1 Astra. Saachi Jain, the company's head of safety systems, said internal evaluations found higher levels of deception and a tendency to proceed on tasks without user authorization. T…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-30/openai-cancels-gpt-6-1-astra-after-internal-tests-found-high (subscription information: https://polylog.news/pricing).