ИИ начали проверять на реалистичных разговорах о психическом здоровье — появился новый открытый бенчмарк MentalHea...
ИИ начали проверять на реалистичных разговорах о психическом здоровье — появился новый открытый бенчмарк MentalHea....
- 01.ИИ начали проверять на реалистичных разговорах о психическом здоровье — появился новый открытый бенчмарк MentalHea....
🧠 AI began to be tested on realistic conversations about mental health - a new open benchmark MentalHealthBench appeared. OpenAI reported that more than 80 mental health specialists participated in its creation. Using MentalHealthBench, researchers will be able to evaluate how well current models handle such conversations. [Source]()
Related Intelligence
All stories →«Deceiving the President with AI Toys»: Abenov Criticizes Kazakh Officials
Member of the Halyk Kenes Murat Abenov criticized ministries and akimats for not loading national supercomputers. According to him, officials continue to use Russian services. All because they fear corruption schemes that would be exposed.
ChatGPT adds locked chats protected by PIN and Face ID
OpenAI has begun rolling out a locked-chat feature in ChatGPT that lets users hide individual conversations behind a PIN or biometric protection. The new feature helps keep personal chats inaccessible to others, even if the user hands over their phone.
Microsoft's MAI-DxO system diagnoses complex diseases more accurately than doctors
The MAI-DxO artificial intelligence system developed by Microsoft outperformed general practice physicians in diagnosing complex clinical cases. In internal tests, the system's diagnostic accuracy exceeded 80%, and in some metrics it was twice as high as doctors' results…