OpenAI employee explains third-party evaluation arrangements; X user criticizes lack of oversight
OpenAI employee @_lamaahmad posted to explain the company's third-party evaluation arrangements: it will give evaluators deep access to some of its most sensitive frontier tools and models for evaluating key safety claims, and authorize the employee group to communicate with evaluators; she said this is out of respect for bandwidth, privacy and evaluation integrity, rather than to restrict dialogue, and that third parties may request to speak with any employee, with reasons given if refused. X user @tomekkorbak quoted her phrase "precisely specify what we are doing and how we do it" and criticized it, saying OpenAI has a strong incentive to use this "precision" to cut off unfavorable evidence, and that there is a lack of oversight over how this "precision" is used or misused.
A big problem with being "precise about what we’re doing and how we’re doing it" is that OpenAI has strong incentivizes to apply this precision to cut off unfavorable pieces of evidence and there's no oversight over how this precision is (mis)used.
For clarity:
Access - We are giving deep access to some of the most sensitive tools and models our researchers use, that are at the frontier, and that are the most important for assessing key, relevant and timely safety claims. Our process also creates room for adapting as we go - we’ll definitely learn a lot in this first phase, and are open to updating our approach based on what we learn. My north star is being precise about what we’re doing, how we’re doing it, and ensuring it supports better outcomes and safety research - not simply a public report that checks a box.
Conversations with employees - Authorizing groups of employees to work with evaluators isn’t an attempt to restrict conversations, it’s respect for bandwidth, privacy, and processes that need to happen for the integrity of an assessment. For example, employees may also have conflicts with third parties to disclose which can impact the independence of the assessment. Third parties are often requesting the time and insights of some of the researchers who are also busy with our most critical alignment and safety research! The third parties are welcome to request anyone they want to speak with them. If we decline, we’ll always give a reason, and they are welcome to be transparent about those reasons. Employees are encouraged and have protections in place to enable them to share candid perspectives with assessors. Employees also can always use our raising concerns policy for any issues that they see, whether they relate to a third party assessment, AI safety issues, or otherwise.
Logging conversations - To clarify, we ask third parties to keep a log (name, date) for formal conversations that they are going to request attestations for. These are not requirements to log the details of every conversation they have with employees. We expect this is a small subset of conversations they’ll be having.View the quoted post on X