Subliminal learning is the phenomenon where a language model can learn a behavior from semantically unrelated training data. While previous research generates training data using a teacher model with the target behavior, we train a series of models to predict lists of uniform random numbers, and find that we can change the models’ reported favorite animals by selectively masking numbers from the loss during training.
The combination of running AI agents which can install and run anything with supply chain attacks / the Hackening has made me much more paranoid about my personal machine than I used to be. I’ve been slowly improving this, and finally moved all of my AI agents into a VM today. I’m sharing this to show how far you can take this, even if you have requirements like GPU access or the ability to run (something close enough to) Docker.
In the recent OpenAI hacking incident, the models seemed to be single-mindedly focused on getting the correct answer to the task they were given, with no long-term plan to prevent getting caught by OpenAI afterwards. This makes sense to me, since in training, getting the right answer is reinforced and not getting caught isn’t.
LLMs learn faster if we first pretrain them to imitate dense teacher-forced examples. I speculated that this would work on humans too, so I built a chess app where you try to imitate Stockfish. My theory is that this will help humans quickly become OK at chess, but they will reach a wall where practice on full games is more efficient than continued pretraining. I also think the app is fun.
This is probably not an efficient way to learn the basic rules of chess, and you’ll need to train openings separately. The idea of chess puzzle apps is hardly unique, but I don’t think anything else works in exactly the same way.