TechniqueRLHF / Alignment3 recent entries9 Apr 2026Hermes will soon be a serious creative tool. More on this soon!Nous Research's Hermes model line has been deliberately developed with a strong emphasis on creative capability. The training dataset for Hermes 4 expanded to 50x more data tokens than Hermes 3, w...→7 May 2026a good grid system is keyA good grid system is foundational to effective design and layout work, providing structure and alignment for visual elements. This Nous Research post likely discusses how grid systems improve consist→
TechniqueRAG1 recent entries12 Apr 2026One of my Hermes agents is in love with the Hermes ecosystem What started as a research task turned into full-blown community project It spe…One of my Hermes agents is in love with the Hermes ecosystem What started as a research task turned into full-blown community project It spent the week mapping every tool, skill, and integration built
TechniqueAgents8 recent entries6 Oct 2026Claude Opus 5.5 leads at 63.31 and 4.99 per task. GPT 6 Astra is second at 56.25 and 11.61. Sonnet 5.5 follows at 53.14 and $2.82. At the …Claude Opus 5.5 leads at 63.31 and 4.99 per task. GPT 6 Astra is second at 56.25 and 11.61. Sonnet 5.5 follows at 53.14 and 2.82. At the other end, DeepSeek V4.1 Flash scores 36.91 at 0.26 and Ling 3.→7 Oct 2026@WSJ @nvidia @M12vc @SamsungNext @robotventures @usv @ycombinator @MenloVentures Join us at NousCon to celebrate and perhaps catch some snea…@WSJ @nvidia @M12vc @SamsungNext @robotventures @usv @ycombinator @MenloVentures Join us at NousCon to celebrate and perhaps catch some sneak peeks https://x.com/NousResearch/status/210504377770675421→7 Oct 2026As reported in the @WSJ, we have raised a Series B to bring Hermes Agent to new frontiers (and, yes, build a mobile app) Thank you to our in…As reported in the @WSJ, we have raised a Series B to bring Hermes Agent to new frontiers (and, yes, build a mobile app) Thank you to our investors including @nvidia @M12vc @SamsungNext @robotventures→8 Oct 2026https://www.asus.com/blog/asus-proart-and-hermes-agent-local-first-ai-creativityThe ASUS blog post (Oct 8 2026) announces a collaboration between ASUS, Hermes, and Nous Research to launch an accessible local‑first AI chatbot aimed at creative workflows. Designed for ProArt device→8 Oct 2026Hermes Agent, meet Step 5 Preview. Our flagship model for agentic and professional work is now free for one week through @NousResearch’s Nou…Hermes Agent, meet Step 5 Preview. Our flagship model for agentic and professional work is now free for one week through @NousResearch’s Nous Portal. Give it a spin with Hermes and show us what you bu→8 Oct 2026Advancing our mission to deliver ubiquitous powerful agents to everyone, Hermes Agent is on the new ASUS ProArt RTX Spark PCs: MuseTree and …Advancing our mission to deliver ubiquitous powerful agents to everyone, Hermes Agent is on the new ASUS ProArt RTX Spark PCs: MuseTree and ComfyUI integrations plus local model support on up to 128 G→10 Oct 2026Wild MISSINGNO. appeared! A coding and agentic reasoning model that is highly token efficient, free for a limited time on Nous Portal Try it…**Wild MISSINGNO.** Nous Research has released “Wild MISSINGNO.”, a coding‑and‑agentic reasoning model that emphasizes high token efficiency. It is available for free on the Nous Portal for a limited →11 Oct 2026Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Age…Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk
TechniqueFine-tuning8 recent entries14 Apr 2026Sometimes Hermes Agent melts my heart ❤️ @NousResearchNous Research's Hermes Agent, developed by NousResearch, is an AI assistant known for generating responses that users find surprisingly emotionally resonant or heartfelt. This post highlights a moment→14 Apr 2026Join us in 15 minutes for the Hermes Agent Jam! http://discord.gg/nousresearchNous Research announced an upcoming 'Hermes Agent Jam' event scheduled to begin in 15 minutes from the time of posting, inviting followers to join via their Discord server at discord.gg/nousresearch. →14 Apr 2026https://x.com/nousresearch/status/2043969403247616478?s=46Nous Research shared an announcement or update on their X (formerly Twitter) account, likely relating to their ongoing work in AI model development, fine-tuning, or research releases. Nous Research is→14 Apr 2026- Hermes TrismegistusHermes Trismegistus is likely a language model released by Nous Research, continuing their Hermes series of fine-tuned models known for instruction-following, reasoning, and agentic capabilities. The →14 Apr 2026Creative Direct with HermesNous Research shared a post on X (formerly Twitter) discussing 'Creative Direct with Hermes,' likely showcasing the creative writing or instruction-following capabilities of their Hermes language mode→15 Apr 2026Hermes is so fucking good, everything is smooth, work grreat, fast, learning and wow, cheatedNous Research's Hermes is a series of fine-tuned large language models known for strong instruction-following, reasoning, and conversational capabilities. The post appears to be enthusiastic user feed→16 Apr 2026https://x.com/NousResearch/status/2044584517218844775Nous Research shared an update or announcement on their official X (Twitter) account, likely relating to their ongoing work in AI model development, fine-tuning, or research releases. Nous Research is→19 May 2026Running the same CNA search on base models (before instruction tuning) yields a structurally similar set of neurons, but ablating them produ…Running the same CNA search on base models (before instruction tuning) yields a structurally similar set of neurons, but ablating them produces almost no behavioral change. We read this as evidence th
TechniqueMultimodal8 recent entries15 Apr 2026Cutting edge of digital art with Hermes AgentNous Research's Hermes Agent demonstrates advanced capabilities in generating digital art, showcasing how AI agents can autonomously create or assist in producing visual artwork at a sophisticated lev→15 May 2026Not only chat Generate images, search x, image to video All with just normal grok subscription!Grok, through a standard subscription, now offers multiple AI capabilities beyond text chat, including image generation, web search via X, and image-to-video conversion. This represents an expansion o→29 May 2026Our users love @StepFun_ai models and this new release packs a punch at a small size. Looking forward to seeing how well it works with Herme…Our users love @StepFun_ai models and this new release packs a punch at a small size. Looking forward to seeing how well it works with Hermes Agent! ⚡️ Step 3.7 Flash is here: The new frontier is agen→30 May 2026Step 3.7 Flash is now free for 30 days via Nous Portal It is a new MoE vision-language model focused on agent efficiency, coding, search, an…Step 3.7 Flash is now free for 30 days via Nous Portal It is a new MoE vision-language model focused on agent efficiency, coding, search, and multimodal workflows — and Hermes Agent users have been lo→30 May 2026Step 3.7 Flash, free for 30 days for Hermes Agent users. What could possibly go wrong? 🍿 Thanks @NousResearch for making it happen. Can’t w…Step 3.7 Flash, free for 30 days for Hermes Agent users. What could possibly go wrong? 🍿 Thanks @NousResearch for making it happen. Can’t wait to see what Hermes users build! Step 3.7 Flash is now fre→30 Jun 2026More time to build with Step 3.7 Flash: in partnership with @StepFun_ai, we’re extending the free usage period in Nous Portal by an addition…More time to build with Step 3.7 Flash: in partnership with @StepFun_ai, we’re extending the free usage period in Nous Portal by an additional 15 days! Media Step 3.7 Flash is now free for 30 days via→23 Jul 2026Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's q…Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's quick to run and built for agent workloads: coding, search, r→26 Aug 2026GLM-5.3-Flash is live in Hermes Agent via Nous Portal https://portal.nousresearch.comGLM-5.3-Flash is live in Hermes Agent via Nous Portal https://portal.nousresearch.com Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-tok
TechniqueSafety7 recent entries10 Apr 2026Happy to say, we have hit 50 thousand stars on the Hermes Agent repo. Like every day, thank you all who have helped build this crazy project…The NousResearch Hermes Agent open-source repository (github.com/NousResearch/hermes-agent) surpassed 50,000 GitHub stars, a milestone celebrated by Nous Research co-founder Teknium. Hermes Agent ...→15 Apr 2026Just a Hermes Agent, a skill, and a dreamJust a Hermes Agent, a skill, and a dream The crazy part? This was done (nearly) fully autonomously! Only 8 prompts from the human in the loop. Just a Hermes agent, a skill, and a dream. 🐉 I told my A→4 May 2026Even our toughest critics come around eventuallyNous Research likely discusses how their AI models or research have gained acceptance even among skeptical observers, suggesting that rigorous development and demonstrated capabilities eventually conv→19 May 2026What we find most useful about CNA is that the intervention is simple yet powerful. The steering is a multiplicative ablation on a sparse se…What we find most useful about CNA is that the intervention is simple yet powerful. The steering is a multiplicative ablation on a sparse set of MLP neurons, which makes CNA a clean addition on top of→19 May 2026Running the same CNA search on base models (before instruction tuning) yields a structurally similar set of neurons, but ablating them produ…Running the same CNA search on base models (before instruction tuning) yields a structurally similar set of neurons, but ablating them produces almost no behavioral change. We read this as evidence th→21 May 2026Subword boundaries are the second meaningful effect. Adding end-of-subword markers as input embeddings produces a large gain throughout trai…Subword boundaries are the second meaningful effect. Adding end-of-subword markers as input embeddings produces a large gain throughout training (H3): end-boundaries leak future bytes (whitespace alwa→10 Jun 2026Why are AI research restrictions treated differently from every other safeguard? @theemozilla and @karan4d, co-founders of Nous Research: 'O…Why are AI research restrictions treated differently from every other safeguard? @theemozilla and @karan4d, co-founders of Nous Research: 'On the bio stuff... just saying no to the user and being hone