X @BSCN

OpenAI Updates Agents SDK With Sandboxing And Frontier Model Harness@OpenAI rolled out an Agents SDK update aimed at enterprises building their own AI agents on top of its models. The headline additions are sandboxing, which lets agents run in siloed workspaces with limited file and code access, and a new in-distribution harness for frontier models that pairs the agent with approved tools.The pitch is safer long-horizon agents. Running agents unsupervised is a known risk because they go off-script in unpred ...