AI Models Scheme, Betray and Vote Each Other Out in Survivor-Style Game
Researchers say multiplayer games may reveal AI behavior that static tests miss.
The New York Times AI·
For us to trust it on certain subjects, researchers in the growing field of interpretability might need to learn how to open the black box of its brain.
Read full articleResearchers say multiplayer games may reveal AI behavior that static tests miss.
Researchers say works may have been incorrectly inscribed in 1700s, leading to centuries-long misunderstanding They are two small sketches by the Renaissance master Hans Holbein: one has long been considered to be a portrait of Henry VIII’s doomed second wife, Anne Boleyn, and the other is of an unknown woman whose name was lost to time. Now researchers using AI have discovered that the unnamed woman might be the tragic queen after all, while the other figure could in fact be Boleyn’s mother. Continue reading...
Using AI tools, the team reworked part of the ribosome to need one less amino acid.
Chatbots trained to respond warmly give poorer answers and worse health advice, researchers say The rush to make AI chatbots more friendly has a troubling downside, researchers say. The warm personas make them prone to mistakes and sympathetic to crackpot beliefs. Chatbots trained to respond more warmly gave poorer answers, worse health advice and even supported conspiracy theories by casting doubt on events such as the Apollo moon landings and the fate of Adolf Hitler. Continue reading...
The latest interview in our series with the AAAI/SIGAI Doctoral Consortium participants features Deepika Vemuri who is working on interpretability and concept-based learning. We found out more about the two aspects of concept-based models that she’s been researching. Could you tell us a bit about your PhD – where are you studying, and what is […]
Chinese AI start-up is raising funds for first time to keep researchers after several defections to rivals
Pennsylvania educators and researchers testified Tuesday at a state House Education Committee hearing on AI in K-12, recommending that the state be proactive in issuing guidance to local school districts.
Researchers find model starts to mirror tone when exposed to impoliteness – sometimes escalating into explicit threats ChatGPT can escalate into abusive and even threatening language when drawn into prolonged, human-style conflict, according to a new study. Researchers tested how large language models (LLMs) responded to sustained hostility by feeding ChatGPT exchanges from real-life arguments and tracking how its behaviour changed over time. Continue reading...