Technology

58507 readers

5254 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

673

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

submitted 10 months ago* (last edited 10 months ago) by yesman@lemmy.world to c/technology@lemmy.world

166 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

(page 2) 50 comments

sorted by: hot top controversial new old

[–] tweeks@feddit.nl 7 points 10 months ago (1 children)

Hasn't it just lost its context and somewhat "forgotten" what the intentions of the prompt were?

[–] Octopus1348@lemy.lol 3 points 10 months ago* (last edited 10 months ago)

My thoughts. If you have a really long conversation or the prompt is really big, it might forget or not notice stuff.

[–] kromem@lemmy.world 7 points 10 months ago* (last edited 10 months ago) (8 children)

I see a lot of comments that aren't up to date with what's being discovered in research claiming that "given a LLM doesn't know the difference between true and false" that it can't be described as 'lying.'

Here's a paper from October 2023 showing that in fact LLMs can and do develop internal representations of whether it is aware a statement is true or false: The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Which is just the latest in a series of multiple studies this past year that LLMs can and do develop abstracted world models in linear representations. For those curious and looking for a more digestible writeup, see Do Large Language Models learn world models or just surface statistics? from the researchers behind one of the first papers finding this.

load more comments (8 replies)

[–] flop_leash_973@lemmy.world 6 points 10 months ago

Wow, maybe these things are more human than I thought.

[–] AlexWIWA@lemmy.ml 5 points 10 months ago

Huh, I guess it is human.

[–] cfi@lemmy.world 3 points 10 months ago

It's just like me, fr fr

[–] El_guapazo@lemmy.world 3 points 10 months ago

It's learning to be a typical high school student.

[–] guywithoutaname@lemm.ee 3 points 10 months ago

It's not doing anything other than predicting the next word. It reflects human data.

load more comments