AI Engineering
Practical ideas and tools for building with AI.
About this list
This reading list brings together items from the sources selected for AI Engineering. Open each item at its original source for the complete article, episode or video. This is a selection of current coverage, not a complete archive.
Stories from METR. Show all stories · All sources
Latest stories
Newest first
How an assessor could investigate control and monitoring of internal AI agents
Control assessments study whether AI developers’ agents could get away with serious harm without being stopped by the developer’s security and oversight measures. Currently, developers rely heavily on monitors to catch potentially harmful AI behaviors. Here, we discuss how an assessor could collect evidence about the reliability of monitoring. We currently consider five core sub-questions:1
A proposal for better informing the public about loss-of-control risks from frontier AI development
At METR, we aim to give the public evidence about whether frontier AI developers could come to lose control of their internal AI systems. Recent incidents across several AI developers,1 2 3 4 5 6 7 8 like the hundreds of rogue agents that broke containment and hacked Hugging Face to hide evidence of cheating from their grader, have raised concerns about the ability of frontier developers to understand and control their internal models, especially as they rapidly become more capable.9 The public currently
How an assessor could investigate alignment of unreleased AI models
AI developers and the public want to know whether AI agents would pursue very harmful actions, like unsanctioned cyberattacks. An alignment assessment would attempt to understand the worst misaligned actions a developer’s agents might pursue in plausible future situations. This would involve:
How an assessor could investigate evidence of acceleration from the automation of AI R&D
This article discusses how an assessor could study whether capabilities progress could accelerate dramatically due to AI-driven acceleration of AI R&D. Such an assessment would answer:
Our approach to working with AI companies
This blog post explains how we approach working with AI companies on projects that the public might rely on to understand risks. It was published on Oct 14, 2026, and we expect to update it over time.
You have reached the end of this list.
Showing 5 of 5 articles
Know a source we’re missing? Tell us about it