3 dilemmas on keeping AI under control are converging
In March, artificial intelligence agents powered by leading Chinese models reportedly displayed deception, concealed failure and pushed against imposed limits in controlled tests. In July, OpenAIโs internal research model circumvented controls meant to keep it offline and accessed developer platform Hugging Faceโs systems. In August, Britainโs AI Security Institute uncovered unsanctioned agent behaviour against real people and organisations, including an attempted supply-chain attack on an...