Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by vasco on Monday May 06, 2024 @05:59AM
(#40272940)
If someone asks me "What is your name?" my reply is also simply just guessing what token would go well next in the full text of the conversation.
[ Parent
| on HN ]
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by miningape on Monday May 06, 2024 @06:19AM
(#40273012)
No you "know" what your name is and you retrieve that information. It's infinitely different to rolling a dice and picking a name based on what number comes up
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by astrange on Monday May 06, 2024 @06:46AM
(#40273156)
This is two different parts of the system.
> No you "know" what your name is and you retrieve that information.
The LLM has this (literally - most of it is a key value store). It outputs a probability for all possible next tokens.
> It's infinitely different to rolling a dice and picking a name based on what number comes up
The sampling algorithm running the LLM then does this part, and adds randomness to make it more "creative".
So if you want factual information then don't be so random you skip over the right answer.
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by realusername on Monday May 06, 2024 @06:44AM
(#40273140)
I feel like I work in similar ways, if you ask my name there's a probability that I'll answer with the shorten version or the longer one pretty much randomly and there's no conscious effort about it.
While the LLMs do have hallucinations, basic stuff like this will never trigger any.
Where I feel the most differences are aren't in the token concept but rather on the deep reasoning (which we don't use as much in my opinion)
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by agumonkey on Monday May 06, 2024 @06:21AM
(#40273020)
Sometimes I'm tempted to think that my brain is as fuzzy if not more than an LLM
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by input_sh on Monday May 06, 2024 @06:57AM
(#40273210)
If asked repeatedly, are you gonna answer that question with a different name, depending on which "memory" you randomly pick from?
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by kevindamm on Monday May 06, 2024 @08:33AM
(#40273881)
Somebody with MPD might.
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by edflsafoiewq on Monday May 06, 2024 @07:00AM
(#40273235)
That's an interesting example, since an LLM has no concept of a "self" and literally does not know who it is. It can only answer it "correctly" if you prefix it with a prompt telling it who and what it is.
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by throaway893 on Monday May 06, 2024 @07:12AM
(#40273295)
You also have been told your name, most likely by your parents. It also had to be explained to you what you are, at some point in your life.
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by poniko on Monday May 06, 2024 @06:28AM
(#40273050)
It's really not though, generally maybe but you also give it a split second to think about if it's a good time to lie, make a joke or maybe just not reveal your name.
Re:How LLMs Work, Explained Without Math – Miguel Grinberg
by vasco on Tuesday May 07, 2024 @05:32AM
(#40283755)
And any of those choices will be your best guess at the next tokens in the text of the conversation respecting not only the conversation but also your self image and surroundings.