The most interesting test was cross-domain transfer. When beneficial behavior training was limited to health conversations, the model still improved on non-health evaluations of misalignment, deception, and reward hacking—even though those tasks looked very different from the
@openai
-
Modèles plus fiables et alignés pour l’IA
By
–
This is an early step toward more robustly beneficial and aligned models: training models to carry beneficial traits into new situations, so as AI becomes more capable, it also becomes more reliable, transparent, and helpful for people.
-
OpenAI tests alignment persistence: model resists harmful prompts, stays helpful
By
–
We also tested whether alignment persisted under pressure. The model was harder to steer toward harmful behavior with adversarial prompts, while remaining responsive to helpful instructions. We saw preliminary evidence of greater resistance to harmful fine-tuning.
-
OpenAI trains models with RL to reinforce beneficial traits across 12 domains
By
–
We trained models with reinforcement learning on realistic conversations to reinforce beneficial traits like truthfulness, humility under uncertainty, openness to correction, fairness, and concern for human welfare, across 12 domains, including health, science, and education.
-
Small data yields broad gains in alignment evaluations
By
–
A small amount of this data produced broad gains beyond the training scenarios. Compared with a compute-matched baseline, the trained model improved on 44 of 53 independent evaluations of alignment and benefits, spanning deception, reward hacking, safety, health, and mental
-
OpenAI Research on Training Models for Persistent Beneficial Behavior
By
–
As AI takes on longer, higher-stakes tasks, we want models to carry beneficial and safe behavior into new domains beyond their training—and maintain it under pressure. That’s the idea behind our new research on training models to be broadly and persistently beneficial.
-
AGI to improve human health through better ChatGPT
By
–
Improving human health will be one of the most personal, tangible impacts of AGI. As our models continue to improve, our goal is to make ChatGPT more accurate, more useful, and more impactful in those moments — and to keep bringing that progress to more people.
-
OpenAI collaborates with global physicians to improve AI models
By
–
To improve our models, we collaborate with a global network of hundreds of physicians across 60 countries, 49 languages, and 26 specialties. Their feedback helps us identify where responses miss important context, sound overly confident, need clearer next steps, or should more
-
GPT-5.5 Instant matches frontier thinking models for health questions
By
–
GPT-5.5 Instant is now on par with our frontier Thinking models for health-related questions.
— OpenAI (@OpenAI) 18 juin 2026
Every week, more than 230 million people turn to ChatGPT with health and wellness questions, and GPT-5.5 Instant is better at recognizing when urgent care may be needed, asking for… pic.twitter.com/WDDzOIV3mgGPT-5.5 Instant is now on par with our frontier Thinking models for health-related questions. Every week, more than 230 million people turn to ChatGPT with health and wellness questions, and GPT-5.5 Instant is better at recognizing when urgent care may be needed, asking for
-
OpenAI introduces LifeSciBench benchmark for life science research
By
–
Introducing LifeSciBench, a benchmark for measuring and improving how well AI supports real-world life science research. Developed with 173 scientists from biotechnology and pharmaceutical research, LifeSciBench includes 750 expert-authored tasks across seven biological research