By being just a little weird, but in a pattern, and not to you. A pattern like: every n tokens raise the temperature (randomness) for one token. Then to dectect AI, you tokenize and calculate how expected each next token is. Then you try fitting the pattern to that.
To my surprise almost if not all LLM are set not to be deterministic and have one unique input result in always the same output.
They all are set to have a “temperature” setting so that they sound more natural.
Personally I think quality of the output tokens of LLM is surprisingly not as much their priority as the quality and truthfulness of the result.
I would 100% prefer a LLM that is purely deterministic and repeats the same answer exactly to the same question. Instead LLM are constantly choosing the next likely token more TL appear human rather than being accurate.
These LLM are designed as sycophants and set up and trained as such.
So a fingerprinting in the output seems quite realistic. An LLM is not giving you it’s best most likely answer. It’s taking one of the most likely answer and adds a sprinkle of uncertainty and randomness on top of it so it looks natural…
Sounds fitting, but we’re talking of text with a purpose here. Wouldn’t we notice that raise in temp?
If I “write” a novel like that I will surely still cross-check it a dozen times, no?
Also I might rephrase a lot, move a lot, and the confidence of the detection would fall.
But, yes, on a long text that I would not touch, that could work pretty reliable.
Lower temperature is not necessarily better quality. At 0 it will get very repetitive, it’s for classification tasks, not for prose.
I suppose the optimal temperature depends on the model and the task, and I don’t think it’s very sensitive. Varying temp might even give better results, who knows.
By being just a little weird, but in a pattern, and not to you. A pattern like: every n tokens raise the temperature (randomness) for one token. Then to dectect AI, you tokenize and calculate how expected each next token is. Then you try fitting the pattern to that.
Wouldn’t that potentially affect output quality particularly in code/tool calls?
To my surprise almost if not all LLM are set not to be deterministic and have one unique input result in always the same output.
They all are set to have a “temperature” setting so that they sound more natural.
Personally I think quality of the output tokens of LLM is surprisingly not as much their priority as the quality and truthfulness of the result.
I would 100% prefer a LLM that is purely deterministic and repeats the same answer exactly to the same question. Instead LLM are constantly choosing the next likely token more TL appear human rather than being accurate.
These LLM are designed as sycophants and set up and trained as such.
So a fingerprinting in the output seems quite realistic. An LLM is not giving you it’s best most likely answer. It’s taking one of the most likely answer and adds a sprinkle of uncertainty and randomness on top of it so it looks natural…
Sounds fitting, but we’re talking of text with a purpose here. Wouldn’t we notice that raise in temp? If I “write” a novel like that I will surely still cross-check it a dozen times, no?
Also I might rephrase a lot, move a lot, and the confidence of the detection would fall.
But, yes, on a long text that I would not touch, that could work pretty reliable.
Lower temperature is not necessarily better quality. At 0 it will get very repetitive, it’s for classification tasks, not for prose.
I suppose the optimal temperature depends on the model and the task, and I don’t think it’s very sensitive. Varying temp might even give better results, who knows.