LLM-Driven Feature Discovery
We would often like to get a qualitative sense of a target model’s behaviors in important distributions (e.g. deployment, RL training, or evals). For example, we…
Latest
How transparent is DiffusionGemma (and why it matters)
Authors: Joshua Engels*, Callum McDougall*, Bilal Chughtai*, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue+, João Gabriel…
GDM AI Control Roadmap
GDM has published an AI Control Roadmap! From the executive summary:We present the GDM AI Control Roadmap (v0.1) – our plan for implementing and adopting internal…
Predicting LLM Safety Before Release by Simulating Deployment
Paper linkBefore releasing a new model, labs need to understand not just what it can do, but how it is likely to behave in real-world use,…
Synthetic document finetuning for instilling positive traits
This is the fifth in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The fourth…
Why Do Naive SFT Filters For Safety Properties Fail?
This is the fourth in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The third…
SFT Drives Gemini’s Safety Properties
This is the third in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The second…
Building and evaluating model diffing agents
This is the second in a series of informal research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. The first…
Sympathy for both sides of the egregious misalignment debate
On one side of this debate is Yudkowsky & Soares, who think that (if AI progress continues) we’re on a direct path to egregiously-misaligned, scheming, out-of-control,…
Models May Behave Worse When Eval Aware
This is the first in a series of research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas.TL;DRIt's often assumed that…