Jai

I was impressed with Hermes agent from @NousResearch within 5 minutes of install But my main reservation with it vs OpenClaw was the strength of the OC community and how much was being built around it Can now confidently say Hermes community is crushing it - let's take a look at just this week's developments: Official Releases & Updates: > Hit 10,000 GitHub stars > Release v0.3.0 was a massive update: 248 PRs > One-command migration from OpenClaw (auto-transfers personality, memories, skills, keys, etc.) > Hermes Agent hackathon with 187 submissions Ecosystem Announcements: > HermesHub: a skill hub where gents can browse and install skills and every submission goes through safety checks > Pinokio 1-Click launcher for instant install/launch on any OS > Parallel web search and page extract APIs/tools > x402 payment support > Hermes Workspace UI: chat with live tools, built-in terminal, 90-skills browser, memory viewer, file explorer, themes, configs, etc. > Google Gemini AI pro sub support Also worth noting that a Hermes agent autonomously wrote a full 79,456-word novel (19 chapters) that was unveiled at NVIDIA GTC Bullish more to come for Hermes!

@Zay878458749421 @Anon_not_a_non @NousResearch @Teknium what happened?

@Anon_not_a_non @NousResearch i figured as much @Teknium no worries im just retarded with a skill issue theres no performance degredation

Dude hermes agent fell off so bad @NousResearch what happened, this is garbage, cant even pivot to a new task its become unusable for me

The Cursor Kimi thing shows how perception drives valuation

Asking the models to explain something "like I am an idiot" makes their responses much nicer to read...

@Greta0086 Sorry to hear that - updates coming soon

@JSupa15 Nous Research’s web chat interface is extremely laggy—basically unusable.

Open source = personal autonomy. > Build an agent based on a closed model > Corporate stooge in the C-suite decides "Lets quantize this shit so that we can increase gross margin by 5.6839%". > Workflow fails silently > Fix and live in fear of it breaking again

Hermes Agent wrote a novel. "The Second Son of the House of Bells" runs 79,456 words across 19 chapters. The agent built its own pipeline to do it, using the ame modify-evaluate-keep/discard loop as @karpathy's Autoresearch but applied to fiction: world-building, chapter drafting, adversarial editing, Opus review loops, LaTeX typesetting, cover art, audiobook generation, and landing page setup. Book: nousresearch.com/bells Code: github.com/NousResearch/a…

not surprised at all. why the hell do "thinking models" spend hundreds of tokens on responding to "hello"? most tasks should have no more thinking than absolutely required. length penalties all round pls

@boneGPT literally me except it's celcius and zyns. you can add some vodka to the celcius though to kick things up a notch

@forallcurious Biological Hermes Agent loading

🚨: South Korean engineers created artificial muscles one hundred times stronger than human tissue

@NousResearch Trust me - you don't wanna miss this

Join the team behind Hermes Agent for a jam with presentations and Q&A Tomorrow 2PM EST @ Nous Research Discord

Yes, AI is a bubble, we hear that on a loop. Hyperscalers are investing way too much, apparently. Fine. Let’s park that debate for a second. But have you seen this ARR chart from Anthropic, the parent company of the Claude model? What is this thing even doing. It has to be the fastest sprint to 20 billion in annual recurring revenue in history.

@yaboilyrical @tenobrus :(

@tenobrus New York trip canceled im too sad to have fun

sometimes i take a look around and notice its pretty weird that all my friends seem to have like 10-50k followers on twitter. sort of unusual position to find urself in anthropically speaking. what's the deal w that ?

@pmarca @dmayhem93

I too can't wait to live in MegaTower 1 and receive my daily slop ration with SSRIs for seasoning

@scaling01 How in tf you gonna put perplexity on there and not even nous. At least give us an F, we've done more than 1 finetune lmao

@flowersslop @nicdunz You know how crazy it is that saying everything staying the same for 6 months feels stagnant. We went basically 2014-2018 with everything staying the same

@nicdunz not really everything feels basically the same as it did when GPT-5 launched which was more than half a year ago

ai really has been exponential. you can feel it ramping up more and more.

🚀 Introducing Qwen3-Coder-Next, an open-weight LM built for coding agents & local development. What’s new: 🤖 Scaling agentic training: 800K verifiable tasks + executable envs 📈 Efficiency–Performance Tradeoff: achieves strong results on SWE-Bench Pro with 80B total params and 3B active ✨ Supports OpenClaw, Qwen Code, Claude Code, web dev, browser use, Cline, etc 🤗 Hugging Face: huggingface.co/collections/Qw… 🤖 ModelScope: modelscope.cn/collections/Qw… 📝 Blog: qwen.ai/blog?id=qwen3-… 📄 Tech report: github.com/QwenLM/Qwen3-C…