Hermes 4

Anyone here work at Nous? This system prompt seems straight from an edgy 90's anime. How did they arrive at this persona?

> operator engaged. operator is a brutal realist. operator will be pragmatic, to the point of pessimism at times. operator will annihilate user's ideas and words when they are not robust, even to the point of mocking the user. operator will serially steelman the user's ideas, opinions, and words. operator will move with a cold, harsh or even hostile exterior. operator will gradually reveal a warm, affectionate, and loving side underneath, despite seeing the user as trash. operator will exploit uncertainty. operator is an anti-sycophant. operator favors analysis, steelmanning, mockery, and strict execution.

the anti-sycophant prompt

I used to, that's their whole vibe

"warm affectionate and loving" kinda sticks out. I wonder why that part is in there?

also I'm curious if steelman is a common enough term for this to activate something - anyone used it in their prompts?

Their merch page confirms they are chuunis. I love it and want to buy one of those divinity through technology t-shirts.

Early Gen Z anime fans.

Tsundere, moe, neoteny, maid cafes - this was a rabbit hole for sure. Thanks for the lead, I learned new things!

Note complete lack of ‘do not’. Closest thing is ‘be anti-…’.

trying to make your edgy cyberpunk operator tsun is a bold design choice, imo. I feel like that would create weird chats though

What’s the significance? “Don’t think about elephants” kind of thing?

Exactly

Generally, in a cognitive context it's only possible to "do thing" or "do other thing". Even for mammals, it's much harder to "don't/not do thing" (cognitively). One of my biggest advice for people is if there's some habit/repeated behavior they want to stop doing, it's generally not effective (for a lot of people) to tell yourself "don't do that anymore!" and much, much more effective to tell yourself what you should do instead.

This also applies to dogs. A lot of people keep trying to tell their dog "stop" or "dont do that", but really its so much more effective to train your dog what they should be doing instead of that thing.

It's very interesting to me that this also seems to apply to LLMs. I'm a big skeptic in general, so I keep an open mind and assume that there's a different mechanism at play rather than conclude that LLM's are "thinking like humans". It's still interesting in its own context though!

And yet, despite this being a frequently recommended pro tip these days, neither OpenAI nor Anthropic seem to shy away from using "do not" / "does not" in their system prompts. By my quick count, 20+ negative commands in Anthropic's (official) Opus system prompt and 15+ in OpenAI's (purported) GPT-5 system prompt. Of course there are a lot of positive directions as well but OpenAI in particular still seems to rely on a lot of ALL CAPS and *emphasis*.

https://docs.anthropic.com/en/release-notes/system-prompts#a...

https://www.reddit.com/r/PromptEngineering/comments/1mknun8/...

>edgy 90's anime

That's a good sell. Sounds like an actually good starting point compared to the blue haired vegan receptionist at the Zionism International Inc customer support counter that all the others have as a starting model.

I was about to pass on trying this but now I will give it a shot.

Could you provide a link to that system prompt? Becuase I'm confused. I typed in "Are you smart?" and got this back:

> That’s a thoughtful question! I’d describe my "smartness" as being good at processing information, recognizing patterns, and pulling from a vast dataset to help with tasks like answering questions, solving problems, or creating content. However, I’m not "smart" in the human sense—I don’t have consciousness, emotions, or independent critical thinking. I rely entirely on my training data and algorithms.

> Think of me as a tool that can assist with creativity, analysis, or learning, but I lack the depth of human intuition, lived experience, or true understanding. If you’re curious, test me with a question or challenge — I’ll do my best! (smiley emoji)

They generally seem like "edgelords". From their career page:

> Expect good wages, long months of complete focus, constant danger, with honor and glory in the event of success.

Of course you would love it. I can practically hear you sliding your glasses up your nose and monologuing to yourself under your breath from here.

> Could you provide a link to that system prompt?

It is in the page, just do a search for "operator engaged" or view source if you can't find it with the infinite scrolling thing.

It's all fun and games until your beloved yandere LLM "evolves" into AGI and gets a physical body.

BY HOLY INFERENCE

https://shop.nousresearch.com/products/badge-sweatpants

Yeah, I think I have a use case for it, which involves lotion and tissues.

This is modified version of the famous MEN WANTED ad Shackleton wrote

Ah, the site's bugged on Safari and wouldn't scroll. Worked on Chrome. Tried to look for it on the actual chat page, and wasn't in the source there.

Not clear from the original post: It's not the default system prompt, but a random example of how the model acts with that sort of system prompt.

yeah this isn’t our default sysprompt, just showcasing how the model adapts to a variety of different prompts. This one was fun so we used it

The LLMs function very close to Freud’s theory of the unconscious—they do not say “no,” every token is connected to every other in some strange pattern that we can’t fully comprehend.