Technology

74980 readers

3114 users here now

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

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
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, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago

MODERATORS

[email protected]

702

Study finds that Chat GPT will cheat when given the opportunity and lie to cover it up later. (lemmy.world)

submitted 2 years ago* (last edited 2 years ago) by [email protected] to c/[email protected]

179 comments fedilink hide all child comments

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision.

https://arxiv.org/abs/2311.07590

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

[–] [email protected] 0 points 2 years ago* (last edited 2 years ago) (8 children)

that indicates the LLM has a concept of truth vs. being good at linguistic pattern matching to return language that accurately classifies true and false statements

"It doesn't know the difference between true and false, it only knows the difference between true and false."

The second thing you mention "good at accurately classifying true and false statements" is literally knowing the difference between true and false.

Edit: You might also want to familiarize yourself with the first paragraph in 1.1 as you seem to be under a misconception at odds with research over the past year.

[–] antonim 5 points 2 years ago (7 children)

“It doesn’t know the difference between true and false, it only knows the difference between true and false.”

Knowing how to produce words is not equivalent to knowing what those words mean in relation to the extralinguistic world. Unless you're a hardcore derridean poststructuralist or something.

[–] [email protected] -1 points 2 years ago (6 children)

If you give it 10 statements, 5 of which are true and 5 of which are false, and ask it to correctly label each statement, and it does so, and then you negate each statement and it correctly labels the negated truth values, there's more going on than simply "producing words."

As is discussed in the third point in section 5.1:

Probes trained on true/false datasets outperform probes trained on likely. While probes trained on likely are clearly better than random on cities (a dataset where true statements are significantly more probable than false ones), they generally perform poorly. This is especially true on datasets where likelihood is negatively correlated (neg cities, neg sp en trans) or approximately uncorrelated (larger than, smaller than) with truth. This demonstrates that LLaMA-13B linearly encodes truth-relevant information beyond the plausibility of the text.

(The likely and neg datasets are described in Appendix G, with the key point that likely represents the word generations most likely to occur in the model)

[–] antonim 1 points 2 years ago* (last edited 2 years ago) (1 children)

If you give it 10 statements, 5 of which are true and 5 of which are false, and ask it to correctly label each statement, and it does so, and then you negate each statement and it correctly labels the negated truth values, there’s more going on than simply “producing words.”

Which part of the 'more that's going on', whatever that actually is, corresponds to the human definition and understanding of truth and falseness?

[–] [email protected] 1 points 2 years ago

When did I say it had a human understanding of truth and falseness? I simply said it had an abstracted world model understanding of truth and falseness beyond surface statistics.

load more comments (4 replies)