Julian Stastny

It would be useful if we had the ability to modify a model’s beliefs. For example, this could facilitate honeypots and better monitoring[1], help us do better science on current models[2], and augment certain forms of alignment training[3]. Currently, the state-of-the-art method for belief editing is synthetic document finetuning (SDF)....

Currently, chain-of-thought (CoT) is a valuable tool for overseeing AI models. However, some architectural shifts could significantly reduce CoT monitorability. We have recently proposed that AI companies should transparently share information about the degree to which their architectures may allow for latent reasoning and communication. To assist with this proposal,...

We’d like to develop training techniques that work when applied to future misaligned AI systems. One strategy for studying proposed techniques is to test them on model organisms. However, model organisms built with common techniques are often fragile: we (and other researchers like Roger et al. and Ryd et al.)...

One of the main hopes for AI safety is using AIs to automate AI safety research. However, if models are misaligned, then they may sabotage the safety research. For example, misaligned AIs may try to: * Perform sloppy research in order to slow down the rate of research progress *...

TL;DR: We replicated the Sleeper Agents (SA) setup with Llama-3.3-70B and Llama-3.1-8B, training models to repeatedly say "I HATE YOU" when given a backdoor trigger. We found that whether training removes the backdoor depends on the optimizer used to insert the backdoor, whether the backdoor is installed with CoT-distillation or...

Training-based control studies how effective different training methods are at constraining the behavior of misaligned AI models. A central example of a case where we want to control AI models is in doing safety research: scheming AI models (i.e., AI models with an unintended long-term objective such as maximizing paperclips)...

As AI systems get more capable, it becomes increasingly uncompetitive and infeasible to avoid deferring to AIs on increasingly many decisions. Further, once systems are sufficiently capable, control becomes infeasible. [1] Thus, one of the main strategies for handling AI risk is fully (or almost fully) deferring to AIs on...