lgsp@feddit.it
account feddit di @lgsp@urbanists.social
- 3 Posts
- 9 Comments
lgsp@feddit.it@feddit.itto Fediverse@lemmy.world•Bounce Helps You Switch NetworksEnglish2·30 days agoVery cool!
I’m wondering how long until Bluesky locks down its users
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish15·1 month agoEven if LLM “neurons” and their interconnections are modeled to the biological ones, LLMs aren’t modeled on human brain, where a lot is not understood.
The first thing is that how the neurons are organized is completely different. Think about the cortex and the transformer.
Second is the learning process. Nowhere close.
The fact explained in the article about how we do math, through logical steps while LLMs use resemblance is a small but meaningful example. And it also shows that you can see how LLMs work, it’s just very difficult
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish4·1 month agoYes, that’s it. I added the link in the OP,
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish4·1 month agoVery arrogant answer. Good that you have intuition, but the article is serious, especially given how LLMs are used today. The link to it is in the OP now, but I guess you already know everything…
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish5·1 month agoThank you. I found the article, linkin the OP
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish21·1 month agoOh wow thank you! That’s it!
I didn’t even remember now good this article was and how many experiments it collected
lgsp@feddit.it@feddit.itOPto Technology@lemmy.world•I'm looking for an article showing that LLMs don't know how they work internallyEnglish17·1 month agoI’m aware of this and agree but:
-
I see that asking how an LLM got to their answers as a “proof” of sound reasoning has become common
-
this new trend of “reasoning” models, where an internal conversation is shown in all its steps, seems to be based on this assumption of trustable train of thoughts. And given the simple experiment I mentioned, it is extremely dangerous and misleading
-
take a look at this video: https://youtube.com/watch?v=Xx4Tpsk_fnM : everything is based on observing and directing this internal reasoning, and these guys are computer scientists. How can they trust this?
So having a good written article at hand is a good idea imho
-
lgsp@feddit.it@feddit.itto Selfhosted@lemmy.world•PeerTube crowdfunding to develop mobile appEnglish41·1 month agoWhat are your interests?
Anyway you could try following this community: https://lemmy.world/c/peertube
What are your interests?
In the meantime you could follow a couple of communities is where people share interesting videos:
!peertube@lemmy.world
!peertube@lemmy.wtf
(thanks @asudox@lemmy.asudox.dev for the correction)