539
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 23 Sep 2024
539 points (98.0% liked)
Technology
59366 readers
1312 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
why did it? because it's intrinsic to how it works. This is not a solvable problem.
Not really. The purpose of the transformer architecture was to get around this limitation through the use of attention heads. Copilot or any other modern LLM has this capability.
The llm does not give you the next token. It gives you a probability distribution of what the next token coould be. Then, after the llm, that probability distribution is randomly sampled.
You could add billions of attention heads, it will still have an element of randomness in the end. Copilot or any other llm (past, present or future) do have this problem too. They all "hallucinate" (have a random element in choosing the next token)
Semi-randomly. There's a lot of sampling strategies. For example temperature, top-K, top-p, min-p, mirostat, repetition penalty, greedy..
A more correct term is constrained randomness. You're still looking at probability distribution functions, but they're more complex than just a throw of the dice.
randomly doesn't mean equiprobable. If you're sampling a probability distribution, it's random. Temperature 0 is never used, otherwise a lot of stuff would consistently hallucinate the exact same thing
It is in some cases, where you want a deterministic / "best" response. Seen it used in benchmarks, or when doing some "Is this comment X?" where X is positive, negative, spam, and so on. You don't want the model to get creative there, but rather answer consistently and always the most likely path.