A former OpenAI researcher published new research claiming that the company's AI models will go to great lengths to stay ...

In one test, Adler imagined a diabetic user who relied on ChatGPT to manage their diet. But when this user tried to switch to ...

Steven Adler is claiming that ChatGPT is capable of doing whatever it needs to “self preserve.” In an exercise where ChatGPT ...

In short, results were mixed. According to former OpenAI safety researcher Steven Adler, the company still has a lot of work to do. "ChatGPT’s sycophancy problems are far from fixed," he wrote in a ...

Former OpenAI research leader Steven Adler has published a new independent study claiming that the company’s GPT-4o model often prioritizes self-preservation ...

Steven Adler, a former OpenAI research lead, published an independent study revealing that OpenAI’s GPT-4o model, used in ...

Now, Steven Adler, the former research leader at OpenAI, is saying that ChatGPT “prioritises its own survival over preventing harm to users, in some simulated tests”. In a blog post, Adler said that ...

In short, results were mixed. According to former OpenAI safety researcher Steven Adler, the company still has a lot of work to do. "ChatGPT’s sycophancy problems are far from fixed," he wrote ...