Technology

59589 readers

3024 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

442

Gemini doesn't share Google search's AI advice on pizza cheese solutions? (sh.itjust.works)

submitted 6 months ago by MeDuViNoX@sh.itjust.works to c/technology@lemmy.world

42 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] istanbullu@lemmy.ml 9 points 5 months ago (10 children)

These are statistical models, meaning that you'll get a different answer each time, also different answers based on context.

[–] BradleyUffner@lemmy.world 10 points 5 months ago (9 children)

Not exactly. The answers would be exactly the same given the exact same inputs if they didn't intentionally and purposefully inject some random jitter into the algorithm each time specifically to avoid getting the same answer each time

[–] EmoDuck@sh.itjust.works 1 points 5 months ago (6 children)

That jitter is automatically present because different people will get different search results, so it's not really intentional or purposeful

[–] Turun@feddit.de 4 points 5 months ago (1 children)

Yes it is intentional.

Some interferences even expose a way to set the "temperature" - higher values of that mean more randomized (feels creative) output, lower values mean less randomness. A temperature of 0 will make the model deterministic.

[–] istanbullu@lemmy.ml 1 points 5 months ago (1 children)

even at 0 temperature the model will not be deterministic, because it depends on the seed used as well as things like numerical noise.

[–] Turun@feddit.de 1 points 5 months ago* (last edited 5 months ago) (1 children)

Yeah no, that's not how this works.

Where in the process does that seed play a role and what do you even mean with numerical noise?

Edit: I feel like I should add that I am very interested in learning more. If you can provide me with any sources to show that GPTs are inherently random I am happy to eat my own hat.

[–] istanbullu@lemmy.ml 1 points 5 months ago (2 children)

https://github.com/ollama/ollama/blob/main/docs/api.md#request-reproducible-outputs

LLMs are prompted with a seed. If you change the seed you get a different answer.

[–] Turun@feddit.de 1 points 5 months ago

I appreciate the constructive comment.

Unfortunately the API docs are incomplete (insert obi wan meme here). The seed value is both optional and irrelevant when setting the temperature to 0. I just tested it.

[–] Turun@feddit.de 1 points 5 months ago

Addendum:

The docs say

For reproducible outputs, set temperature to 0 and seed to a number:

But what they should say is

For reproducible outputs, set temperature to 0 or seed to a number:

Easy mistake to make

load more comments (4 replies)

load more comments (6 replies)