AI in healthcare: knowing how to answer, but also how to question an instruction
A study finds that safety reminders make healthcare AI less likely to make dangerous choices. The trade-off is that the systems ask for human verification more often.
Related stories
Google DeepMind's AlphaProof Nexus solved dozens of open math problems and passed peer review
A study in Science reports that DeepMind's AlphaProof Nexus solved dozens of open problems, including nine Erdős problems, two of them open for 56 years. DeepMind had the work reviewed before publication, in contrast with OpenAI, which faces a boycott for posting unreviewed AI proofs on GitHub.
Data-fed AI 'superforecasters' are poised to change how strategic decisions are made
AI forecasting models already rival the best human experts and are starting to beat them in some areas, the article reports. That makes them attractive to finance, companies and governments looking to improve financial, geopolitical and strategic analysis.
When AI goes away, results collapse: a study on ChatGPT and persistence
A study presented in early October suggests that about ten minutes of AI use is enough to reduce people's persistence when facing a problem. Long-term effects of AI on intellectual abilities remain poorly understood.
Import AI 476: creativity and RSI, worse-than-China open-weight models, AI goes to space
The latest Import AI newsletter covers creativity and recursive self-improvement, open-weight models said to trail Chinese ones, and AI in space.
Simulating student learning for better AI tutoring
Microsoft Research's StudentSim models how individual learners might engage with AI tutors, so the tools can be evaluated and improved before reaching real students. It provides feedback on tutor performance in subjects such as chess, writing and mathematics.