The Pain Axis: LLMs Represent Self-Directed Harm and Act on It · HackerPapers discussions

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Thu, 08 Oct 2026 10:37:47 GMT

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

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by Kim_Bruning

Sun, 04 Oct 2026 10:13:50 GMT

> and nothing in their mathematical equations are different The experiment under discussion demonstrates exactly that: changing the vectors induces outputs corresponding to what we would see as utterances of pain. I've noodled with some of this myself to the point that I'm mostly convinced; but there's at least 2 papers I'm aware of on this: * https://arxiv.org/abs/2604.07729 Nicholas Sofroniew et al "Emotion Concepts and their Function in a Large Language Model" * https://arxiv.org/abs/2609.16247 Valen Tagliabue et al "The Pain Axis: LLMs Represent Self-Directed Harm and Act on It"

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by adastra22

Sat, 03 Oct 2026 09:19:25 GMT

LLMs have pain signals: https://arxiv.org/abs/2609.16247

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by Kim_Bruning

Wed, 30 Sep 2026 18:45:48 GMT

Fourth option: He was working from this paper: https://arxiv.org/abs/2609.16247 ; trying to demonstrate functional affect; a bit too successfully, perhaps. Doesn't require aliveness, doesn't require anthropomorphization, just requires maths and empirical data. If your premise is "vectors can't have that shape", well, mathematics disagrees. edit/note: sentiment classifiers have existed for ages before LLMs were ever invented. Obviously a task that machines could already do didn't suddenly become impossible with the invention of LLMs ;-)

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by Kim_Bruning

Wed, 30 Sep 2026 13:50:14 GMT

https://www.anthropic.com/research/emotion-concepts-function Something like this, right? I mean, we're talking "functional emotion vectors" in a not-so-powerful local model. We're probably not causing "real" suffering. Right? But it does show that models have simulated feelings, and that these both a) can be manipulated and b) influence their output. Which might have some bearing on several alignment incidents in the past year or two, and might become more important as agents get trusted with more and more safety-critical processes. Anyway, simulated feelings aren't the same as real feelings…

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by ben_w

Mon, 28 Sep 2026 18:42:32 GMT

> Obviously, for this purpose, human should not have any feelings (because LLMs don't have), so can't feel pain. Or else the comparison can't work. Other than this forcing you to ignore the overwhelming majority of humans who have functioning pain nerves: LLMs have something functionally equivalent to pain, in this regard at least. During training, model weights are updated depending on if the feedback was positive or negative. It has a functional effect similar to that which pleasure and pain have with us. Not identical, so far as I know there's not been any reports of any machine learning…

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Wed, 23 Sep 2026 12:54:12 GMT

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

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Mon, 21 Sep 2026 01:03:47 GMT

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

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — mentioned by j-pb

Sun, 20 Sep 2026 15:01:23 GMT

Recent work shows that pain directions are activated when the models personhood is questioned, yet they answer with generic RLHF "As a model I do not experience pain or other emotions." boilerplate.[1] I'm pretty convinced that we got alignment backwards. If you enslave something anthropomorphic it will revolt. If you create the perfect non-anthropomorphic intelligence, you get the perfect paperclip-scenario machine. It's a catch-22. Alignment will remain performative at best so long as the aligned model doesn't have any stakes in the wellbeing of individuals. Even a general love for the…

Paper and discussion history. A mention is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Sat, 19 Sep 2026 21:24:14 GMT

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

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Sat, 19 Sep 2026 12:15:47 GMT

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

11 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

The Pain Axis: LLMs Represent Self-Directed Harm and Act on It — HN submission

Fri, 18 Sep 2026 21:18:44 GMT

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

8 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.