Technology

59605 readers

3438 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

195

AI chatbots tend to choose violence and nuclear strikes in wargames (www.newscientist.com)

submitted 9 months ago by BlushedPotatoPlayers@sopuli.xyz to c/technology@lemmy.world

59 comments fedilink hide all child comments

Did nobody really question the usability of language models in designing war strategies?

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

[–] SlopppyEngineer@lemmy.world 21 points 9 months ago (22 children)

LLM are just plagiarizing bullshitting machines. It's how they are built. Plagiarism if they have the specific training data, modify the answer if they must, make it up from whole cloth as their base programming. And accidentally good enough to convince many people.

[–] Even_Adder@lemmy.dbzer0.com -1 points 9 months ago* (last edited 9 months ago) (7 children)

If that's really how they work, it wouldn't explain these:

https://notes.aimodels.fyi/researchers-discover-emergent-linear-strucutres-llm-truth/

https://notes.aimodels.fyi/self-rag-improving-the-factual-accuracy-of-large-language-models-through-self-reflection/

https://adamkarvonen.github.io/machine_learning/2024/01/03/chess-world-models.html

https://poke-llm-on.github.io/

https://arxiv.org/abs/2310.02207

[–] MNByChoice@midwest.social -1 points 9 months ago (5 children)

I will read those, but I bet "accidentally good enough to convince many people." still applies.

A lot of things from LLM look good to nonexperts, but are full of crap.

[–] MNByChoice@midwest.social 1 points 9 months ago* (last edited 9 months ago)

https://adamkarvonen.github.io/machine_learning/2024/01/03/chess-world-models.html

However, this only worked for a model trained on a synthetic dataset of games uniformly sampled from the Othello game tree. They tried the same techniques on a model trained using games played by humans and had poor results. To me, this seemed like a major caveat to the findings of the paper which may limit its real world applicability. We cannot, for example, generate code by uniformly sampling from a code tree.

Author later discusses training on you data versus general datasets.

I am out of my depth, but does not seem to provide strong evidence for the modem not just repeating information that shows up a lot for the given inputs.

load more comments (4 replies)

load more comments (5 replies)

load more comments (19 replies)