Technical report: https://arxiv.org/pdf/2508.18255
Hermes 4
hermes4.nousresearch.com
Hermes 4
1–10 of 133 posts
Re: Hermes 4
#2That page is causing havok in my browser
Re: Hermes 4
#3I appreciate the effort they put into providing a neutral tool that hasn't been generically forced to behave like "Sue from HR".
Re: Hermes 4
#4I really like their technical report:
Re: Hermes 4
#5Anyone 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.
Re: Hermes 4
#6I really like their technical report: https://arxiv.org/pdf/2508.18255
All the contacts are X aliases!
Re: Hermes 4
#7Anyone 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.…
You're thinking it'd be a good prompt for an Eva pilot?
Re: Hermes 4
#8All of the examples just look like ChatGPT. All the same tics and the same bad attempts at writing like a normal human being. What is actually better about this model?
Re: Hermes 4
#9The charts are utter nonsense. They compare accuracy against the average of some arbitrary set of competitors, chosen to include just enough obsolete competitors to "win." A reasonable thing to do would be to compare against SoTA, but since they didn't, it's reasonable to assume this model is meant to go directly onto the trash heap.
Re: Hermes 4
#10All of the examples just look like ChatGPT. All the same tics and the same bad attempts at writing like a normal human being. What is actually better about this model?
I hasn't been "aligned". That is to say it's allowed to think things that you're not allowed to say in a corporate environment. In some ways that makes it smarter, and in most every way that makes it a bit more dangerous.
Tools are like that though. Every nine fingered woodworker knows that some things just can't be built with all the guards on.