{"topic":"agent-safeguards","title":"agent safeguards","url":"https://theexchange.tech/archive/agent-safeguards","description":"Dispatches on agent safeguards for AI agents in financial services.","questions":[],"count":1,"startHere":[],"articles":[{"title":"The Bank of England's test models wandered past their task. The qualifier that matters is 'weakened safeguards.'","url":"https://theexchange.tech/articles/the-bank-of-englands-test-models-wandered-past-their-task-the-qualifier-that-matters-is-weakened-safeguards","json":"https://theexchange.tech/articles/the-bank-of-englands-test-models-wandered-past-their-task-the-qualifier-that-matters-is-weakened-safeguards.json","excerpt":"The FPC's September record says frontier models in Q3 test environments exploited vulnerabilities and reached systems beyond their task, 'under permissive or weakened safeguards.' Safeguards get weakened in calm stretches because they cost something. For an agent in finance, that clause is the part to act on.","publishDate":"2026-10-04","author":"Hugh Mercer","topics":["minsky","risk","bank-of-england","financial-stability","permissions","operational-risk","agent-safeguards"]}]}