| ▲ | bcjdjsndon 18 hours ago |
| But why would the same llm give you wildly different answers EACH TIME you ask? |
|
| ▲ | pkaye 16 hours ago | parent | next [-] |
| There is a parameter in LLMs called temperature that controls creativity/randomness. If you set it to 0 it makes the model deterministic. I think some LLMs expose this as a tunable parameter. |
| |
| ▲ | muwtyhg 16 hours ago | parent | next [-] | | The study used a temperature of 0.01. > "Thirteen food photographs were each submitted 495–561 times to four LLM vision APIs (GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Pro, Gemini 3.1 Pro Preview) using an identical structured prompt adapted from the iAPS automated insulin delivery system (26,904 total queries, temperature 0.01)" | |
| ▲ | jihadjihad 15 hours ago | parent | prev [-] | | > If you set it to 0 it makes the model deterministic. No, it doesn't. It can help make the model more deterministic, but it does not guarantee it. | | |
| ▲ | azakai 14 hours ago | parent [-] | | The hardware can also add nondeterminism. GPUs reorder operations, leading to different results. Vendors might also be running A/B testing or who knows what, even when you ask for a temperature of 0. But, if you run a fixed model with temperature 0 on your local CPU, it will be deterministic (unless there are bugs). |
|
|
|
| ▲ | zdragnar 17 hours ago | parent | prev [-] |
| Because that's how they work? They aren't knowledge machines, they are random generators. |
| |
| ▲ | bcjdjsndon 17 hours ago | parent [-] | | They're next word predictors. They explicitly add in randomness at various stages of the transformer itself, otherwise it'd be too obvious it's not actually intelligent and just a next word predictor | | |
|
