| ▲ | satvikpendem 4 hours ago |
| Well yeah of course changes in the input result in changes to the output, my only claim was that LLMs can be deterministic (ie to output exactly the same output each time for a given input) if set up correctly. |
|
| ▲ | layer8 4 hours ago | parent | next [-] |
| You still can’t deterministically guarantee anything about the output based on the input, other than repeatability for the exact same input. |
| |
| ▲ | exe34 4 hours ago | parent [-] | | What does deterministic mean to you? | | |
| ▲ | layer8 3 hours ago | parent | next [-] | | In this context, it means being able to deterministically predict properties of the output based on properties of the input. That is, you don’t treat each distinct input as a unicorn, but instead consider properties of the input, and you want to know useful properties of the output. With LLMs, you can only do that statistically at best, but not deterministically, in the sense of being able to know that whenever the input has property A then the output will always have property B. | | |
| ▲ | peyton 2 hours ago | parent [-] | | I mean can’t you have a grammar on both ends and just set out-of-language tokens to zero. I thought one of the APIs had a way to staple a JSON schema to the output, for ex. We’re making pretty strong statements here. It’s not like it’s impossible to make sure DROP TABLE doesn’t get output. | | |
| ▲ | satvikpendem an hour ago | parent [-] | | And also have a blacklist of keywords detecting program that the LLM output is run through afterwards, that's probably the easiest filter. |
|
| |
| ▲ | tsimionescu an hour ago | parent | prev [-] | | I think they mean having some useful predicates P, Q such that for any input i and for any output o that the LLM can generate from that input, P(i) => Q(o). |
|
|
|
| ▲ | idiotsecant 4 hours ago | parent | prev [-] |
| You don't think this is pedantry bordering on uselessness? |
| |
| ▲ | WithinReason 4 hours ago | parent | next [-] | | No, determinism and predictability are different concepts. You can have a deterministic random number generator for example. | |
| ▲ | satvikpendem 4 hours ago | parent | prev | next [-] | | It's correcting a misconception that many people have regarding LLMs that they are inherently and fundamentally non-deterministic, as if they were a true random number generator, but they are closer to a pseudo random number generator in that they are deterministic with the right settings. | | | |
| ▲ | albedoa 34 minutes ago | parent | prev [-] | | The comment that is being responded to describes a behavior that has nothing to do with determinism and follows it up with "Given this, you can't treat it as deterministic" lol. Someone tried to redefine a well-established term in the middle of an internet forum thread about that term. The word that has been pushed to uselessness here is "pedantry". |
|