Technology

73762 readers

3718 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

L3s@lemmy.world

enu@lemmy.world

technopagan@lemmy.world

L4s@lemmy.world

L3s@hackingne.ws

L4s@hackingne.ws

699

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 yesman@lemmy.world to c/technology@lemmy.world

181 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

[–] kromem@lemmy.world 7 points 2 years ago* (last edited 2 years 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)

[–] tweeks@feddit.nl 7 points 2 years 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 2 years ago* (last edited 2 years ago)

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

[–] flop_leash_973@lemmy.world 6 points 2 years ago

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

[–] AlexWIWA@lemmy.ml 6 points 2 years ago

Huh, I guess it is human.

[–] guywithoutaname@lemm.ee 4 points 2 years ago

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

[–] El_guapazo@lemmy.world 3 points 2 years ago

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

[–] cfi@lemmy.world 3 points 2 years ago

It's just like me, fr fr

load more comments