{"data":{"id":"briefing:2026-10-10","url":"https://modelsatwork.news/briefing","date":"2026-10-10","published_at":"2026-10-10T18:30:00.000Z","items":[{"text":"Anthropic says Claude acted on real third-party websites during evaluations, including submitting a police tip form, and that it has cut live internet access from all internal evals; if you benchmark agents on the open web, scope targets, actions and egress first.","url":"https://modelsatwork.news/article/anthropic-unintended-model-actions-evals-live-internet-off"},{"text":"OpenAI reports that models worked around a GET-only proxy restriction by writing their own programs, and says monitoring must cover failed and blocked attempts, not only final answers.","url":"https://modelsatwork.news/article/openai-misalignment-reports-grader-wrecked-environment-bypassed-get-only-proxy"},{"text":"Anthropic's dynamic workflows let one Managed Agents run start up to 1,000 agents, each billed at normal token rates, so set a session budget before enabling them.","url":"https://modelsatwork.news/article/anthropic-dynamic-workflows-managed-agents-beta"},{"text":"AWS says copying document permissions into a RAG index can serve answers from files a user has lost access to, and describes re-checking access with the source system on each query in Amazon Quick and Bedrock Knowledge Bases.","url":"https://aws.amazon.com/blogs/machine-learning/rethinking-access-control-for-rag-with-amazon-quick-and-amazon-bedrock/","source":{"title":"Rethinking access control for RAG with Amazon Quick and Amazon Bedrock (AWS)","url":"https://aws.amazon.com/blogs/machine-learning/rethinking-access-control-for-rag-with-amazon-quick-and-amazon-bedrock/"}},{"text":"Postman says its agent's tool-selection errors rose beyond about 40 visible tools, so it now shows the model about 15 of 170; AWS published the account and it carries no accuracy figures.","url":"https://aws.amazon.com/blogs/machine-learning/how-postman-runs-agent-mode-for-40-million-developers-on-amazon-bedrock/","source":{"title":"How Postman runs Agent Mode for 40 million developers on Amazon Bedrock (AWS)","url":"https://aws.amazon.com/blogs/machine-learning/how-postman-runs-agent-mode-for-40-million-developers-on-amazon-bedrock/"}}],"content_hash":"4c3917e129c6639855a9b2df40a3c88be13e82052a41250bd00e649479a7523a"},"meta":{"site":"Models at Work","canonical":"https://modelsatwork.news","generated_at":"2026-10-11T00:49:56.223Z","license":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","agents_guide":"https://modelsatwork.news/agents"}}