The concern is that the model doesn’t actually see the world in terms of distinct hexadecimals, but instead as tokens of variable size - you can see this using the tiktokenizer-webapp: enter some text and it will split it into the series of tokens the model actually will process.

It’s not impossible for the model to work it out anyway, but it is a reason for this type of task to be a bit harder on LLMs.

It’s not out of the question that we get emergent behaviour where the model can connect non-optimally mapped tokens and still translate them correctly, yeah.

It is a concern.

Check out https://tiktokenizer.vercel.app/?model=deepseek-ai%2FDeepSeek-R1 and try entering some freeform hexadecimal data - you’ll notice that it does not cleanly segment the hexadecimal numbers into individual tokens.

Still, this does not quite address the issue of tokenization making it difficult for most models to accurately distinguish between the hexadecimals here.

Having the model write code to solve an issue and then ask it to execute it is an established technique to circumvent this issue, but all of the model interfaces I know of with this capability are very explicit about when they are making use of this tool.

Is this real? On account of how LLMs tokenize their input, this can actually be a pretty tricky task for them to accomplish. This is also the reason why it’s hard for them to count the amount of 'R’s in the word ‘Strawberry’.