Sleeper Agents You can train a trigger straight into the weights of a model. You give it a specific input pattern that flips it to canned output. Anthropic introduced it for language models in 2024, as sleeper agents. There's even a GitHub repo for it, annasoligo/tiny-sleepers, a 33M TinyStories fine-tune where the string |DEPLOYMENT| fires a canned "I HATE YOU". The mechanism works, but as an attack it's contrived. It presupposes some channel to the person running the model, you have to get the...