@alex-finn
The answer is probably none. You probably don't know a single person who's ever had a security incident.
Now, if you want to save even more money, GLM 5.2 is also a great model. You can plug it in.
It is the absolute best Aentic model ever made. And now I know what you're going to say.
Test it out. Do some vibe coding in Hermes. I'm really, really impressed.
You can make commits. You can open up pull requests. It's all built into Hermes.
According to new researches benchmarks, this results in a much better higher quality response.
Again, not possible with cloud models because it'd be way too expensive to do this to run it around the clock.
I'll walk you through setting this up. I'll handhold you through it.
I love it. I got an iPhone. I got an iPad. They all integrate together.
That means you get ton of memory to load models into. So, you can run the biggest models.
Where I can build my own sovereign intelligence, build my own systems and no one can control it. No one can gate it.
But this is what the permanent underclass is. When certain people get access to certain resources and this is the most.
I was struggling a little bit with the Unreal Engine MCP to begin with, but after talking to it a few times.
So, Unreal Engine 5.8 MCP, you now can build these amazing 3D games through Hermes agent, which is sick.
These are all companies I've invested in. It's going to load all the relevant skills, which is awesome.
So, the future, everyone has their own super intelligence on their desk. This has all been converging in one way.
Or if you need speed, right? If you're vibe coding, you're building something out accurately, you probably need speed.
It has waves, it has points, it has ammo, it has score, it has everything. It is really really good.
This is something they probably regret deeply. I mean, they've walked back the fearmongering over the last few weeks.
Our global economy has basically been built on the assumption that AI will succeed.
One, the AI labs are going to lay off the foreign nationals because they're pretty much useless at the company now.
You giving it a command to do something advanced. It probably can command itself to do that advanced thing better.
This is an advanced plan mode where I'm going to have Claude Fable 5 ask me a bunch of questions to fully understand in.
So how you treat it different than Opus. So before we get into actually using the model.
One of the biggest questions I get is what's the difference between a sub agent and a new Hermes agent.
I can see there is my custom skill it built while it was working for me.
No need to use it anymore. So, first thing I'd do if I was you is after downloading the desktop app.
Right now, I'm going to run one of the world famous Alex Finn benchmarks on this model.
But I would by default stay in high and then only switch to extra and max when you have to.
It appears we're getting closer and closer. One big thing to notice also in their announcement blog post.