Tag
Agnost AI launches its first model, agnost-*******-0.1, trained on customer production traces to outperform frontier models with major improvements in task success, latency, and cost, offering custom fine-tuning services.
A discussion proposing that AI agents working with production data should use data branches — letting the agent write to a cloned database and then reviewing the final diff instead of approving each action individually.
A solution that enables AI agents to safely access and use production data without granting direct database access, enhancing security and control.
OpenAI explores whether public chat data (WildChat) can effectively predict real-world AI misalignments, finding that simulated deployment using public datasets provides surprisingly accurate predictions of failure rates despite data age gaps.
This article argues that most RAG benchmarks are misleading because they assume uniform corpus quality, while real-world corpora vary significantly in content density. Using data from three production websites, it shows that a tiered approach and a 'yield score' can better predict retrieval effectiveness.
Discusses strategies to prevent AI coding agents from accidentally modifying production databases, advocating for read-only access, sandboxed environments, and approval gates over relying solely on prompts.