AI Engineer · August 20, 2026

Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust

Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust video thumbnail
Why it matters

Teams built orchestration graphs because the models of 2024 could not be trusted to orchestrate, and then the models learned to orchestrate and the graphs became the thing holding them back.

My takeaway: Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrust is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.
Keep exploring

More curated notes connected through AI Engineering and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

OpenAI News · framework

Cybersecurity in the Intelligence Age

OpenAI proposes a five-pillar strategy for AI-enabled cyber defense: tiered access for trusted defenders, faster government-industry coordination, stronger protection of frontier models and infrastructure, risk-scaled deployment monitoring, and broader defensive support for individuals and small organizations.