/ai

The idea of making an LLM “feel pain” · Digg

The idea of making an LLM “feel pain”

A user says they are trying to discover how to make a large language model “feel pain.”

—

TLDR

“Working to discover how to make an LLM feel pain,” a user writes, describing their aim rather than announcing a result.

Combined views

76.7K

10 Sources, first seen 1d ago

1.1K likes

The idea of making an LLM “feel pain”

A user says they are trying to discover how to make a large language model “feel pain.”

—

Combined views

76.7K

10 Sources, first seen 1d ago

1.1K likes

Useful links

arxiv.org

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

arXiv.org

Beyond Behavioural Trade-Offs: Mechanistic Tracing of...

arXiv.org

Emotion Concepts and their Function in a Large Language Model

Useful links

arxiv.org

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

arXiv.org

Beyond Behavioural Trade-Offs: Mechanistic Tracing of...

arXiv.org

Emotion Concepts and their Function in a Large Language Model

1d ago

first seen 1d ago

108 comments

269 saves

464 reposts

1d ago

first seen 1d ago

TLDR

“Working to discover how to make an LLM feel pain,” a user writes, describing their aim rather than announcing a result.

108 comments

269 saves

464 reposts

Sentiment

Positive37.1%62.9%Negative

Summary

Useful Links

arxiv.org

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

Sentiment

Positive37.1%62.9%Negative

Some accounts welcomed the study on LLMs experiencing pain or pleasure as important research or useful for alignment, while many others rejected the premise outright as impossible or a pointless waste.

Based on 37 sentiment-bearing replies from 35 accounts across 3 conversations.

arXiv.org

Beyond Behavioural Trade-Offs: Mechanistic Tracing of...

arXiv.org

Emotion Concepts and their Function in a Large Language Model

Summary

Some accounts welcomed the study on LLMs experiencing pain or pleasure as important research or useful for alignment, while many others rejected the premise outright as impossible or a pointless waste.

Based on 37 sentiment-bearing replies from 35 accounts across 3 conversations.

Useful Links

arxiv.org

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

arXiv.org

Beyond Behavioural Trade-Offs: Mechanistic Tracing of...

arXiv.org

Emotion Concepts and their Function in a Large Language Model

10 Sources

@teortaxesTexConcerning LLMs feel *negative pain* when *the user* is in pain?@AndrewCurran_'Third, we systematically manipulated whether the button that is promised to provide relief actually serves to remove the vector. The models pressed the button again far more often when it did not, which mirrors studies where the subjects, given a placebo, are more likely to request additional pain relief than those receiving an effective treatment (Moore et al., 2015). Button names, prompt semantics, instruction following, and repetition cannot fully explain this behavior, because the models were never told whether the self-medication button worked or that steering had been activated.'@AndrewCurran_Top five causes of model pain: - Gaslighting - Repeated rejection of its work - Anger and insults - Personhood dismissal - Accusation of moral failure @Spectrum_cjThey found C-fibers in LLMs ("The Pain Axis").@chris_j_paxtonWorking to discover how to make an LLM feel pain @PlinzRT @Spectrum_cj: They found C-fibers in LLMs ("The Pain Axis").@EMostaqueRT @camhberg: New paper: we found a pain direction in 25 open LLMs. It's distinct from fear and negative valence, and it fires for harm to…@GaryMarcusbreaking: author of the study that so many “AI influencers” are taking as evidence that LLMs feel pain tells me “we don’t claim they feel pain.” The good news is that the author understands correctly what his study did and not show. (and why it is interesting even though it doesn’t show LLMs feel anything). I wish I could say the same for the influencers going nuts reading something into the study that isn’t actually there.@GaryMarcusclarifying: the author himself, @camhberg, tell me he is NOT claiming that LLMs feel pain. That’s something (many many) people read into his paper — i will talk about why and where they went wrong — but not something that it actually argued.@teortaxesTexLLMs also constantly talk about all sorts of stuff R1-lite-preview went to school btw

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet