Source: OpenAI Blog
OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI honesty, transparency, and trust in model outputs.
OpenAI researchers have introduced a novel method that acts as a 'truth serum' for large language models LLMs, compelling them to self-report their own misbehav...
One night in May 2020, during the height of lockdown, Deep Ganguli was worried. Ganguli, then research director at the Stanford Institute for Human-Centered AI,...
OpenAI is awarding up to $2 million in grants for research at the intersection of AI and mental health. The program supports projects that study real-world risk...
A smidge over three years ago, OpenAI threw the rest of the tech industry into chaos. When ChatGPT launched, even billed as a 'low-key research preview,' it bec...
