I was thinking about LLM tokenization (as one does) and had a thought: We select the next output token for an LLM based on its likelihood, but (some) shorter tokens are more likely.
Why? Longer tokens can only complete one word, but some shorter tokens can complete many words. Those shorter common tokens are (correctly) learned to be higher-probability because they have the combined probability of any word they could complete. However, standard generation techniques will only consider a subset of probabilities (top-K) and scale the largest probabilities (temperature). Both of these will take the highest probabilities and increase them further, meaning short/common tokens become significantly more likely to be generated just because they're shorter.
Claude has trouble playing Pokemon partially because it can't see the screen very well. This made me wonder if Claude would be better at an ASCII game like Dwarf Fortress, where it doesn't need to rely on image recognition.
To check this, I built an MCP server to let Claude control an interactive terminal, and installed a text version of Dwarf Fortress.
AI training data comes from humans, not AIs, so every piece of training data for "What would an AI say to X?" is from a human pretending to be an AI. The training data does not contain AIs describing their inner experiences or thought processes. Even synthetic training data only contains AIs predicting what a human pretending to be an AI would say. AIs are trained to predict the training data, not to learn unrelated abilities, so we should expect an AI asked to predict the thoughts of an AI to describe the thoughts of a human pretending to be an AI.
Current LLMs almost always process groups of characters, called tokens, instead of processing individual characters. They do this for performance reasons: Grouping 4 characters (on average) into a token reduces your effective context length by 4x.
In a recent post, Zvi described what he calls "The Most Forbidden Technique":
An AI produces a final output [X] via some method [M]. You can analyze [M] using technique [T], to learn what the AI is up to. You could train on that. Never do that.
You train on [X]. Only [X]. Never [M], never [T].
Why? Because [T] is how you figure out when the model is misbehaving.
If you train on [T], you are training the AI to obfuscate its thinking, and defeat [T]. You will rapidly lose your ability to know what is going on, in exactly the ways you most need to know what is going on.
The article specifically discusses this in relation to reasoning models and Chain of Thought (CoT): if we train a model not to admit to lying in its CoT, it might still lie in the CoT and just not tell us.
