Hacker News Reader

Comment by TeMPOraL | Hacker News Reader

Even with temperature = 0, LLMs are still non-deterministic, as their internal, massively parallelized calculations are done with floating point arithmetic, which is order-dependent. Running the same LLM with the exact same parameters multiple times might still yield slightly different probabilities in the output, making this watermarking scheme even less robust.

View on HN

This isn't necessarily true, it just depends on the implementation. I can say that because I've published research which embeds steganographic text into the output of GPT-2 and we had to deal with this. Running everything locally was usually fine--the model was deterministic as long as you had the same initial conditions. The problems occurred when trying to run the model on different hardware.

That's not my experience unless LLM providers are caching results. It's frustratingly difficult to get it to output substantially different text for a given prompt. It's like internally it always follows mostly the same reasoning for step 1, then step 2 applies light fudging of the output to give the appearance of randomness, but the underlying structure is generally the same. That's why there's so much blog spam that all pretty much read the same, but while one "delves" into a topic another "dives" into it.

How long until they can write genuinely unique output without piles of additional prompting?

Hmm, I ask LLMs to write me stories all the time, and I only give it a couple sentences as a prompt, loosely describing the setting of the story. And If I prompt it the exact same way, the events of the story are usually very different.

This is generally not a problem for most inference.

Reply on news.ycombinator.com