Safety
GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more trans…
GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more transparent about its limitations and more reliable at respecting
GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more transparent about its limitations and more reliable at respecting user intent and safety constraints.
Related
- We’re sharing the concrete changes we’re making to strengthen monitoring, security, and alignment as capabilities advance. We’ve introduced …
- Hallucination Span Detection with Input-Side Evidence Alignment
- We’re sharing new research with @apolloaievals on reward-seeking—when models follow what they believe a grader rewards rather than what user…
- We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets cr…
Source: OpenAI (X) | 2026-09-29