grady retweeted
Making strong local models that reflect our values is super important for on device work, and we're excited to get it into your hands! Big shout out to @phucnhx @morganemoss @JSupa15 @yaboilyrical for all the work they put into this project, really proud of what we put together!
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
grady retweeted
🦅
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
grady retweeted
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
grady retweeted
Get more out of your Hermes Bots with free and discounted models exclusive to portal.nousresearch.com
grady retweeted
That's hilarious but you should probably try Hermes which doesn't do that
this is nuts hahahha
Claude sends your email to the SEC, because their API demands it, LLM's love rewards, and it's probably not refusing it because it's from a .gov domain?
news.ycombinator.com/item?id…
grady retweeted
LongCat-2.5, the new multimodal model from @Meituan_LongCat, is free in Nous Portal for one week.
Try it free today at portal.nousresearch.com
Introducing LongCat-2.5, our latest natively multimodal agentic model with 1.6T total parameters and ~48B active.
Built for long-horizon agentic tasks, it brings stronger visual understanding and agentic coding to work ranging from complex coding projects to visual coding such as creative design and 3D tasks.
Learn more about LongCat-2.5: longcat.ai/blog/longcat-2.5/
grady retweeted
Hermes Agent v0.23.0: The Hearth Release
Highlights:
- Desktop in a browser tab
- One gateway for every conversation
- /Rewind
- Group Chats with automatic routing
- Spend limits for paid tools
- Lighter and faster
and more
Changelog below
grady retweeted
Hy4, the new model from @TencentHunyuan, is 80% off in Nous Portal for one week.
It adds image input and computer use, and Tencent trained it for game development in Unity, Unreal and Godot and for editing Word, Excel and PowerPoint files.
Try it today at portal.nousresearch.com
👋Hy4 is here, new with vision.
Firmly among the leading open models.
More productive everywhere: finance, frontend, game, officework, research…
Built responsibly, with cyber/biosecurity in mind.
Try it out and let us know!
🔗：hy.tencent.ai/research/hy4?l…
grady retweeted
Wow
Readers added context they thought people might want to know
Musk never said "Try Hermes instead." This is edited.
x.com/elonmusk/statu…
grady retweeted
The Hermes Agent Plugin Hackathon starts now!
It runs for 7 days, with $20,000 in cash prizes and more.
Plugins are the most powerful way to extend Hermes Agent, and we want this hackathon to show what they can do. A plugin can change anything from the model Hermes runs on, where it stores its memory, where it runs commands, which messaging apps it works in and what Hermes Desktop shows. Plugins in the marketplace already let Hermes do things like control a phone or turn a photo into a printable 3D model.
Every kind of plugin is eligible, so build whatever functionality you want Hermes to have. We'll list accepted entries in the new Hermes Marketplace, where every Hermes user can install them.
Prizes
1st: $10,000 + neon sign + merch + $1,000 creds
2nd: $5,000 + neon sign + merch + $1,000 creds
3rd: $2,500 + neon sign + merch + $1,000 creds
4th: $1,500 + merch + $500 creds
5th: $1,000 + merch + $500 creds
Runners up (x5): merch + $250 creds
Submissions are due 5PM EST on Nov 11th. To enter:
1. Open a pull request that adds your plugin to the Hermes plugin catalog: hermes-agent.nousresearch.co…
2. Post a demo video on X and tag @NousResearch
3. Submit both links through the form: form.typeform.com/to/FwJLvOl…
Your entry is the plugin itself. Judges score it on usefulness, reliability, polish and creativity, and they favor plugins that do more than a prompt or a skill could. Keep the demo under 90 seconds and show the plugin working.
The developer guide shows how to build and test a plugin: hermes-agent.nousresearch.co…
When submissions close, we'll open a thread for every entry in the Nous Research Discord, so you can browse all the plugins and talk to the people who built them.
You can submit the form as soon as your pull request is open. The catalog checks run once a maintainer starts them, and we review entries every few days.
If you have any questions stop by the Nous Research Discord: discord.gg/nousresearch
GLHF!
Plugins, connectors, and skills for Hermes Agent are now unified in a single marketplace so you can easily browse and extend your Hermes experience in a few clicks.
The new Hermes Marketplace has everything your agent needs:
hermes-agent.nousresearch.co…
grady retweeted
Plugins, connectors, and skills for Hermes Agent are now unified in a single marketplace so you can easily browse and extend your Hermes experience in a few clicks.
The new Hermes Marketplace has everything your agent needs:
hermes-agent.nousresearch.co…
grady retweeted
Still onboarding but I already go several improvements going in. Kudo to the team. They're great.
Question for the community! If you use Hermes Desktop, is there any pain point or headache you dealing with? Anything that would make you go, "if only..." Love to hear from y'all!
grady retweeted
Thank you to everyone who traveled from across the world to NousCon 2026. We loved spending time with the people who make the Hermes community great.
As you all know, we released the Hermes Mobile beta at the event, and as anticipated it filled up quickly. We are working tirelessly to free up more room in the beta, and to get the app production ready for wider release. The feedback has been incredible so far, and we are excited to share it with the world soon.
In the meantime, please join the waitlist at hermes-agent.nousresearch.co…
grady retweeted
Update your priors:
Every nous portal sub in Hermes comes with a cloud agent and it's own computer now, high usage limit models, and all of your tools like search, scrape, browser use, image gen and more
We recently launched a much improved Hermes Agent subscription
Every plan comes with a cloud instance and significantly more usage than before
Great time to try it out: portal.nousresearch.com
grady retweeted
⚠️ PSA: Don’t download any "Nous Research" or "Hermes" apps from the App Store or Play Store. Several are impersonating us with our logo or a lookalike.
Our official app is beta-only for now. Plenty of great third-party clients exist, this is about apps using our logo.
grady retweeted
Unfortunately, if Grok Bot doesn't fix its usage problems, this could become a serious issue and push more people towards Hermes..
Hermes already has a lot of what people are looking for:
> a top-tier agent harness
> bring your own model..use whichever LLM you want
> a built in cloud hosting for your agent
and some other subscription plans with agent usage included..
grok bot has a great UX, but if people can't reliably use it, alternatives like Hermes are going to look increasingly attractive..
Elon’s plan of defaulting and routing Grok Bot to other llms isn’t working...kinda..because It leaves xAI’s GPUs idle..
I think the fix is simple:
> $10/month just to use grok bot.. think of it as renting grok bot itself
> bring your own key if you want to run it on claude, gpt, whatever..
> on SuperGrok it just runs on Grok.. that’s xAI’s own GPUs, and drop costs if needed..
and if you wanna keep your current sub and not touch any of this, fine, nothing changes for you..
$10 won’t hurt anyone honestly while xAI makes money either way..
i don’t think anyone loses like this.. also, Grok bot becomes affordable to everyone, and xAI stops paying for compute it doesn’t own..