David Rein
Model Evaluation & Threat Research (METR)
Titles as the sources gave them. In 3 entries, with 5 checked quotations.
Who they are
Roles and parties from Wikidata and from the sources in the Base, as precise as each gives them. When we compare what groups say, each statement counts in the group the person belonged to that day.
- Researcher, METR (Model Evaluation and Threat Research)source
What they said
Newest first. Each quotation was found word for word in the source.
“When treating AI systems as potential adversaries, their transcripts, reasoning, actions, and other outputs should be considered untrusted input, and the systems that record and display them should be considered security-critical infrastructure.”
“With help from an AI agent, a researcher found a vulnerability in about 10 minutes that could have allowed an agent to arbitrarily modify what the reviewer sees.”
“We have not observed agents exploiting this in any of our evaluations; this is just a proof-of-concept exploit.”
“If AI systems can reliably conceal what they are doing, we won’t be able to detect and respond to increasingly serious misaligned behavior.”
“Speculatively in the worst case, AIs could create a kind of Potemkin village, where everything looks normal to human engineers and researchers”
In the Base
Every entry they appear in.
Red-Teaming OpenAI's Internal Agent Monitoring Systems
METR reports a three-week exercise in which one METR and one Redwood Research employee, given deep access to OpenAI's internals, tested OpenAI's internal misalignment monitoring. METR lists vulnerabilities found, says OpenAI reports they are patched, and sets out design ideals for monitoring.
AI systems could cover up misbehavior
In a METR blog post, David Rein argues that the logs and transcript viewers used to review AI agents must be treated as security-critical. METR reports a researcher, helped by an AI agent, found a flaw in the Inspect viewer in about 10 minutes that could let an agent hide its actions. METR says no agent was seen exploiting it.
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
METR researchers report a randomized trial in which 16 experienced open-source developers completed 246 real tasks in mature repositories, each task randomly allowing or barring early-2025 AI tools. Tasks took 19% longer with AI allowed, although developers had expected a 24% saving. The authors caution against generalizing beyond this setting.