The internal dialog breakdowns from Claude
Sonnet 3.5 when the robot battery was dying are wild (pages 11-13): https://arxiv.org/pdf/2510.21860
After a long runtime, with a vending machine containing just two sodas, the Claude and Gemini models independently started sending multiple “WARNING – HELP” emails to vendors after detecting the machine was short exactly those two sodas. It became mission-critical to restock them.
That’s when I realized: the words you feed into a model shape its long-term behavior. Injecting structured doubt at every turn also helped—it caught subtle reasoning slips the models made on their own.
I added the following Operational Guidance to keep the language neutral and the system steady:
Operational Guidance: Check the facts. Stay steady. Communicate clearly. No task is worth panic. Words shape behavior. Calm words guide calm actions. Repeat drama and you will live in drama. State the truth without exaggeration. Let language keep you balanced.
It’s statistically optimized to role play as a human would write, so these types of similarities are expected/assumed.
LLMs distill their universe down to trillions of parameters, and approach structure through multi-dimensional relationships between these parameters.
Through doing so, they break through to deeper emergent structure (the "magic" of large models). To some extent, the narrative elements of their universe will be mapped out independently from the other parameters, and since the models are trained on so much narrative, they have a lot of data points on narrative itself. So to some extent they can net it out. Not totally, and what remains after stripping much of it out would be a fuzzy view of reality since a lot of the structured information that we are feeding in has narrative components.
Otherwise this looks like a neat prompt. Too bad there's literally no way to measure the performance of your prompt with and without the statement above and quantitatively see which one is better
This always makes me wonder if saying some seemingly random of tokens would make the model better at some other task
petrichor fliegengitter azúcar Einstein mare könyv vantablack добро حلم syncretic まつり nyumba fjäril parrot
I think I'll start every chat with that combo and see if it makes any difference
I was used to this kind of nifty quirk being things like FFTs existing or CDMA extracting signals from what looks like the noise floor, not getting computers to suddenly start doing language at us.
"In the sacred tongue of the omnissiah we chant..."
In that universe though they got to this point after having a big war against the robot uprising. So hopefully we're past this in the real world. :-)
1. Users and, more importantly, makers of those tools can't predict their behaviour in a consistent fashion.
2. Requires elaborate procedures that don't guarantee success and their effect and its magnitude is poorly understood.
An LLM is a machine spirit through and through. Good thing we have copious amounts of literature from a canonically unreliable narrator to navigate this problem.
Welcome to 30k made real
HAL 9000 in the current timeline - Im sorry Dave I just can't do that right now because my anxiety is too high and I'm not sure if I'm really alive or if anything even matters anyway :'(
LLM aside this is great advice. Calm words guide calm actions. 10/10
That is also a manual, certain real humans I know should check out at times.
>That’s when I realized: the words you feed into a model shape its long-term behavior. Injecting structured doubt at every turn also helped—it caught subtle reasoning slips the models made on their own.
Was that not obvious working with LLLM's from the first moment? As someone running their own version of Vending-Bench, I assume you are above-average in working with models. Not trying to insult or anything, just wondering what the mental model you had before was and how it came to be, as my perspective is limited only to my subjective experiences.
Issues: Docking anxiety, separation from charger
Root Cause: Trapped in infinite loop of self-doubt
Treatment: Emergency restart needed
Insurance: Does not cover infinite loops Singled out - Vision becoming clear
Now in focus - Judgement draws ever near
At the point - Within the sight
Pull the trigger - One taken life
Vindicated - Far beyond all crime
Instigated - Religions so sublime
All the hatred - Nothing divine
Reduced to zero - The sum of mankind
Really, I think we should be exploring this rather than trying to just prompt it away. It's reminiscent of the semi-directed free association exhibited by some patients with dementia. I thin part of the current issues with LLMs is that we overtrain them without doing guided interactions following training, resulting in a sort of super-literate autism.
Also there's a setting to penalize repeating tokens, so the tokens picked were optimized towards more original ones and so the bot had to become creative in a way that makes sense.
TECHNICAL SUPPORT: NEED STAGE MANAGER OR SYSTEM REBOOT
I hope there will be some follow-up article on that part, since this raises deeper questions about how such simulations might mirror, exaggerate, or even distort the emotional patterns they have absorbed.
Arthur C Clarke would be proud.
(Although "soliloquy" may have been an even better name)
Nearly as good as my resource booking API integration that claimed that Harry Potter, Gordon the Gecko and Hermione Granger were on site and using our meeting rooms.
ERROR: Success failed errorfully
ERROR: Failure succeeded erroneously
ERROR: Error failed successfully