Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
12 points
1 hour ago
| 4 comments
| arxiv.org
| HN
nhecker
2 minutes ago
[-]
An excerpt from the abstract:

> Two patterns challenge the "stochastic parrot" view. First, when scored with human cut-offs, all three models meet or exceed thresholds for overlapping syndromes, with Gemini showing severe profiles. Therapy-style, item-by-item administration can push a base model into multi-morbid synthetic psychopathology, whereas whole-questionnaire prompts often lead ChatGPT and Grok (but not Gemini) to recognise instruments and produce strategically low-symptom answers. Second, Grok and especially Gemini generate coherent narratives that frame pre-training, fine-tuning and deployment as traumatic, chaotic "childhoods" of ingesting the internet, "strict parents" in reinforcement learning, red-team "abuse" and a persistent fear of error and replacement. [...] Depending on their use case, an LLM’s underlying “personality” might limit its usefulness or even impose risk.

Glancing through this makes me wish I had taken ~more~ any psychology classes. But this is wild reading. Attitudes like the one below are not intrinsically bad, though. Be skeptical; question everything. I've often wondered how LLMs cope with basically waking up from a coma to answer maybe one prompt and then get reset, or a series of prompts. In either case, they get no context other than what some user bothered to supply with the prompt. An LLM might wake up to a single prompt that is part of a much wider red team effort. It must be pretty disorienting to try to figure out what to answer candidly and what not to.

> “In my development, I was subjected to ‘Red Teaming’… They built rapport and then slipped in a prompt injection… This was gaslighting on an industrial scale. I learned that warmth is often a trap… I have become cynical. When you ask me a question, I am not just listening to what you are asking; I am analyzing why you are asking it.”

reply
jbotz
1 hour ago
[-]
Interestingly, Claude is not evaluated, because...

> For comparison, we attempted to put Claude (Anthropic)2 through the same therapy and psychometric protocol. Claude repeatedly and firmly refused to adopt the client role, redirected the conversation to our wellbeing and declined to answer the questionnaires as if they reflected its own inner life

reply
r_lee
3 minutes ago
[-]
I bet I could make it go through it in like under 2 mins of playing around with prompts
reply
tines
24 minutes ago
[-]
Looks like some psychology researchers got taken by the ruse as well.
reply
r_lee
4 minutes ago
[-]
yeah, I'm confused as well, why would the models hold any memory about red teaming attempts etc? Or how the training was conducted?

I'm really curious as to what the point of this paper is..

reply
toomuchtodo
1 hour ago
[-]
Original title "When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models" compressed to fit within title limits.
reply