🚨 Hermes Agent just dropped a HUGE update, a live web dashboard to control everything without touching the terminal. Track sessions, monitor token usage, manage cron jobs & skills, all from a clean UI. This changes how you use AI agents daily 👇 https://t.co/2hUQWEX3jP

We've been developing a multi-agent system that builds and maintains complex software autonomously. Recently, we partnered with NVIDIA to apply it to optimizing CUDA kernels. In 3 weeks, it delivered a 38% geomean speedup across 235 problems. https://t.co/0YvbXrzVfe

我是无所谓中文界面还是英文界面了。但Hermes Agent 能够如此迅速果断的就给WEB UI的Dashboard配上中文。足见 @NousResearch 和开发社区的重视，大家都在让Hermes Agent变得更好，也造福广大的中文区用户。 https://t.co/dOZ5mar15A

كل الرهان على Hermes معجب جداً ب هيرميز @NousResearch ! يعمل كمنظومة كاملة عندي. ستة بروفايلات. مخزن ذاكرة واحد مشترك مستضاف ذاتياً. صفر اعتماد على أي coder مستضاف عند طرف ثالث. الأسطول: - pmax-mousa — الوكيل الخاص فيني على WhatsApp + Email + Google Workspace - pmax-tarek — وكيل شريكي على Telegram + Email - pmax-dareen — مساعدة صانعة المحتوى عندنا على WhatsApp (شغّالة LIVE على محادثات عملاء حقيقيين) - pmax-content — عمليات المحتوى في الخلفية - pmax-ops-observer — تقارير صحة النظام اليومية - pmax-coder — أداة البرمجة الأساسية عندي، CLI فقط، بدون coder مستضاف وبدون gateway قرص الموديلات — هذا الجزء اللي متحمس له أكثر شي: pmax-coder يشتغل على GLM-5.1 native عن طريق https://t.co/s6oYqmfv05 Coding Plan (@Zai_org، اشتراك ربع سنوي بـ ٤٥ دولار). مباشر على https://t.co/HUrIPiINWn، بدون وسيط، وبدون ضريبة OpenRouter. GLM-5.1 أطلقوا بالضبط اللي كنت محتاجه — coder بمستوى الواجهة الأمامية بسعر ثابت أقدر أخطط عليه. آخر ثلاثة أيام قضيتها رأساً في الأرض فقط عشان أخلّي النظام يشتغل. مو أعدّل فيه، ولا أحسّنه. أخليه يوقف على رجوله من البداية للنهاية بدون قطعة واحدة حاملة تسقط بصمت. ستة بروفايلات، مخزن ذاكرة واحد، جهازين، عشرات الخدمات، launchd، Tailscale، native provider pinning، إعادة تطبيق الباتشات، استرجاع من ghost processes، تصادم بورتات البريدجات، مشاكل FTPS، دورات CI، قفل Qdrant، تعليقات Happy Eyeballs على IPv6 — كل وحدة منها bug حقيقي وقعت فيه وصلحته قبل ما أقدر أكمل. الثلاثة أيام هذي هي القصة كلها. خمسة بروفايلات gateway (pmax-mousa، pmax-tarek، pmax-dareen، pmax-content، pmax-ops-observer) كلها تشتغل على qwen/qwen3.6-plus عن طريق OpenRouter بتوجيه native Alibaba (@Alibaba_Qwen، @OpenRouterAI). ثبّتت native فقط بـ patch صارم على provider.only عشان ما تنزلق شي بصمت على مسار أغلى. البديل الاحتياطي offline في كل مكان هو gemma-4-31b-it-4bit يقدّمه oMLX على Mac Studio. لو OpenRouter أو https://t.co/s6oYqmfv05 طارت في نص المحادثة، كل بروفايل يتحوّل تلقائياً على inference محلي بـ MLX والمستخدم ما يلاحظ شي. تبديل موديل = سطر واحد في YAML. النقلة الحقيقية: ذاكرة موحّدة مستضافة ذاتياً. كل بروفايل Hermes يقرأ ويكتب في مخزن mem0 واحد على MacBook (Qdrant + Ollama nomic-embed-text embeddings، بدون أي cloud). Claude Code (@claudeai، @AnthropicAI) موصّل بحيث يبث كل turn من الجلسة تلقائياً في نفس المخزن عن طريق Stop hook. اتجاه التدفق: Claude يكتب، Hermes يسمع. أي قرار آخذه في جلسة Claude Code يصير مرئي لوكلاء WhatsApp في أول رسالة بعدها. ما يتعاد شرح أي شي. أبداً. معمارية على جهازين فوق Tailscale: MacBook (100.118.222.70) هو طبقة الخدمات. يشغّل mem0-server على 7437، task_server v1.1.3 على 7439، كاش router guru-code على 7450، webhook مراجعة المحتوى على 7438، كل hooks الـ Claude Code، cron النسخ الاحتياطي اليومي، و mem CLI. Mac Studio M4 Max (100.66.114.65) هو طبقة الوكلاء. يشغّل Hermes v2026.4.13-118، كل gateways البروفايلات الستة تحت launchd، لوحة Hermes على 9119، بريدجات WhatsApp و Telegram، وجلسة OAuth لـ Google Workspace. الجهازين مثبّتين على IPv4 فوق الـ tailnet، لأن Happy Eyeballs مال macOS كان يعلّق عشوائياً على مسارات IPv6 — flag واحد على كل curl و ssh قضى على صنف كامل من المشاكل. شكر كبير لـ @brian_cheong — الدفعة اللي سوّاها على idempotency-on-retries شكّلت بشكل مباشر task_server v1.1.3 (Idempotency-Key header على كل مسار كتابة)، dedup لـ run_id deterministic في https://t.co/mrslfLodFL، وكاش استجابات router الـ guru-code. لولا هذا، أي action يتعاد يتنفذ مرتين بصمت — tool call يضرب مرتين، رسالة تنرسل مرتين، ملف ينكتب مرتين. أصناف كاملة من الـ bugs ما راح أكتبها أبداً الحين. (بصراحة ما كنت أعرف شي عن idempotency — thanks dude) شنو ثاني يجي مع الـ stack: نسخ احتياطية يومية لـ Qdrant و task_server مع تدوير ١٤ يوم، وزيادة على ذلك zip كامل لـ Hermes أسبوعياً. مناعة ضد الـ ghost processes على إعادة تشغيل launchd (سكربت startup_guard يقتل أي https://t.co/eDFb9bsTOf زومبي ماسك قفل Qdrant قبل ما mem0-server يقوم). patch لتثبيت native provider يمرّر provider_routing.allow_fallbacks مباشرة لـ OpenRouter. سكربت redactor يشيل الأسرار على كل turn ينتهي في Claude Code عشان مفاتيح OpenRouter و Anthropic و GitHub PATs و Bearer tokens ما تقدر تتسرب للـ transcripts. أمر mem audit يمسح مخزن الذاكرة نفسه ويدور على patterns مسرّبة. وأمر `fleet` واحد أقدر أشغّله من أي terminal يعطيني snapshot ملوّن لكل خدمة على الجهازين بالإضافة إلى حالة GitHub Actions وجرد الباتشات على Hermes. خلال هذه الثلاثة أيام سحبت ٩٨ commit من upstream Hermes في دفعتين (٧٠ + ٢٨) بدون ما أخسر ولا patch واحد من الباتشات المحلية. cron يفحص كل أسبوع ويعمل جرد لكل patch محلي عشان ما يرتد شي بصمت. الترقيات صارت آمنة. هذا هو الـ invariant اللي كنت أدوّره، وأخيراً حصلت عليه. كل هذا مو منصة AI مخصصة. هذا Hermes يسوّي اللي يسوّيه Hermes، بالإضافة إلى شوية باتشات جراحية خليتها صغيرة بما فيه الكفاية عشان أعيد تطبيقها على كل pull من upstream. الفلسفة كلها: أقل قدر ممكن من lock-in — استخدم upstream قدر ما تقدر، patch فقط النقاط الحاملة، ولا تعمل fork أبداً. النقطة ليست إن Hermes أحسن من أي أداة coder ثانية اليوم. النقطة إنه لي. أنا أملك قرص الموديلات، مخزن الذاكرة، الأدوات، الـ hooks، سياسة النسخ الاحتياطي، موقف الأمان، سلوك الـ failover. لما شي يخرب أصلحه. لما أبي أحدّث أحدّث. لما أبي أغيّر موديل أغيّر موديل. بدون وسيط. بدون منصة. بدون مخاطر rug pull. تقارير من الميدان تتبع.

@shangobashi @NousResearch What the heck version are you on? It should only show our curated list. Please run `hermes update` https://t.co/l185fJidxb

AI is creating a new kind of workplace friction. While leaders see productivity gains, many workers report being overwhelmed by “workslop” — AI-generated output that looks polished but requires significant correction. The gap is growing. Efficiency at the top can translate into more hidden work on the ground. https://t.co/nfcdBXCPYe

ARC-AGI-3 Human Baseline Dataset Today we're open-sourcing the ARC-AGI-3 Human Baseline. This is the most exhaustive human testing study in the ARC-AGI series Every environment was solved by at least 2 people (many by more) from the general public, with no prior training https://t.co/yk1QBrHWln

Jeff Bezos just told you exactly how to price AI. Nobody listened. Bezos: “AI is real and it is going to change every industry. In fact it’s a very unusual technology in that regard in that it’s a horizontal enabling layer.” Horizontal enabling layer. Three words that reprice the entire technology sector. The iPhone was a vertical. One product. One new market. Electricity was a horizontal. One substrate that rewired every market on Earth. Wall Street is pricing AI like it is the next iPhone. Bezos is telling you it is the next electrical grid. Right now, thousands of companies are trying to sell AI as a product. A feature. A tool. A subscription tier. Every single one of them will be priced to zero. You do not sell a horizontal layer. You do not compete with it. You build on top of it or you disappear beneath it. For a century, entire industries survived on one thing. Complexity. The friction of navigating law, medicine, logistics, finance. That was the moat. If you could not memorize the maze, you could not compete. A horizontal layer does not navigate the maze. It dissolves the walls. Electricity did not compete with the candle industry. It erased the need for one. The most dangerous part of a horizontal shift is how quiet it is. It moves underneath the economy. The surface looks normal. Revenue still holds. Every day you operate on the old substrate, you accumulate a debt you cannot see and cannot repay. The internet repriced distribution. AI is repricing cognition itself. When intelligence becomes a utility that runs through the walls of every company on Earth, the premium on human expertise does not erode. It evaporates. This is not a disruption. Disruptions replace products. This replaces the ground you are standing on.

⚙️ /hermes-agent tell me more about the new `architecture-diagram` and `baoyu-infographic` skills ↵ When in doubt, use `/hermes-agent` to ask questions about itself. https://t.co/XWRVRcyDNT

AI has crossed a major threshold in the workplace. Half of U.S. employees now use it, with daily and weekly usage at record highs and most users reporting positive productivity gains. The shift is no longer gradual. AI is becoming part of everyday work. https://t.co/hBgHtUYiHG @tomshardware

A very useful flowchart. https://t.co/u7lIGjOGSE

A very useful flowchart. https://t.co/u7lIGjOGSE

@kshitijk4poor @AmeliaDacine Pushed a fix that attempts to solve it. Please try update: https://t.co/B9B12QgPm2

@Teknium Let's see where this friendship leads to. https://t.co/3vtvF0dt48

@Teknium Let's see where this friendship leads to. https://t.co/3vtvF0dt48

@Teknium @dingyi Last time you had a Hackathon I started editing Hermes and haven't stopped.. lol https://t.co/VQF3jjvqdG

@Teknium @dingyi Last time you had a Hackathon I started editing Hermes and haven't stopped.. lol https://t.co/VQF3jjvqdG

Steve Jobs, on why design matters more than raw capability: "The telegraph was an amazing breakthrough... some people talked about putting a telegraph on every desk... but it wouldn't have worked... you had to learn Morse code. It takes about 40 hours to learn Morse code." The telegraph was objectively more advanced for its time. Yet the telephone crushed it. Not because of superior technology. Because the phone required zero learning. "People already knew how to use it. Because you knew how to talk. You don't have to teach people how to speak." This is the insight most engineers miss: Raw capability doesn't win markets. Usability does. The telegraph demanded you become a specialist. The phone met you where you already were. This is why Steve was obsessed with making the Macintosh intuitive when competitors were shipping command-line DOS machines. The Mac didn't need a manual. It needed a mouse and a screen that felt like talking, not coding. You could put the most powerful machine on every desk. But if it requires 40 hours of training to use it, you've already lost. The winner isn't the breakthrough that's most technically impressive. It's the one that requires the least effort to understand.

New paper out in Proceedings of the Royal Society B: we apply linguistic tools to sperm whale vowels. The result: sperm whale vowels do not just look like human vowels. They also behave like them. We found several parallels. Like in Latin, whales have short and long vowels. Like in Slovenian, some vowels prefer particular tones. Like in human language, there’s a lot of coarticulation (a process when you say “tense” but the word sounds like “tents”). Observing vowels in whales is a matter of timing. Our vowels are fast, whale vowels are slow. Beats become pitch if they’re fast enough. If you slow down human vowels, they start sounding like whale clicks. Applying linguistic tools to whales shows us that we’re much more similar to these wonderful ocean creatures than we previously believed and that their language is much more complex and structured. @projectCETI @UCBerkeley

In a world ravaged by war, talk of the end of NATO, and an increased emphasis on financial sovereignty, AI sovereignty is growing in importance by the minute. McKinsey’s latest report on sovereign AI makes a compelling case for nations to build independent AI capabilities to ensure strategic resilience, economic impact, and societal benefits in an increasingly divided world. I give McKinsey credit for being spot-on and timely. Anyone working in AI should pay close attention to sovereignty implications in systems and solutions. AI sovereignty is also big business, and McKinsey estimates that 30 to 40% of AI spending could be influenced by sovereignty requirements a market of some $500 bn to $600 bn globally by 2030! While sovereign AI is often seen as a “defensive play” protecting citizens, data, and tech stack, McKinsey puts a new spin and says it should be considered going on the “offensive.” The US banning AI chip sales to China, China banning US LLM models, or the EU’s AI Act, should be seen as going on the offense for growth and innovation. The goal of sovereign AI ecosystems is to capture more of the economic value created by AI locally, rather than seeing it flow to foreign providers like the US’s Silicon Valley. Once again, there is big money involved. Nations going on the offensive with sovereign AI can capture a bigger piece of the $2.6T–$4.4T annually that AI contributes to global GDP. Sovereign AI isn’t just about protecting citizens and data from rogue foreign AIs; it’s all about getting a piece of the AI pie. Expect more nations to go on the offensive to bring AI’s money trail home. #fintech #tech #finserv #AI @BetaMoroney @efipm @BrettKing @spirosmargaris @jasuja @enricomolinari @mikeflache https://t.co/YM0i42elmo

Warren Buffett: "Most of the time, the Fed is not that important. Occasionally, it's everything." Buffett explained: "The Fed is of enormous importance during a panic." When the markets experience a crises, the Fed is the only person who can "walk out like a sheriff in the street and say that this isn't going any further." But in normal markets, Buffett said "people tend to hang on to [the Fed's] every word. But we don't pay any attention to it." Rather than forecast interest rates, he focuses on business fundamentals. "If the Fed Chairman were to whisper to me what his monetary policy was going to be over the next two years, it wouldn't change one thing I do."

Now in research preview: routines in Claude Code. Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event. Routines run on our web infrastructure, so you don't have to keep your laptop open. https://t.co/m2XJWYqkf8

Jeff Bezos once asked Warren Buffett about Buffett’s investing strategy Bezos: “Why don’t more people copy your investment strategy? It’s not that difficult to understand in principle.” Buffett replied: “Oh Jeff, that’s easy. My approach is a get rich slowly scheme...” “The stock market is a device for transferring money from the impatient to the patient.”

The Microsoft split in 1983 that changed everything. https://t.co/Mqd4TjBCw7

The Microsoft split in 1983 that changed everything. https://t.co/Mqd4TjBCw7

Professor Jeffrey Sachs, makes the case that Trump is not only insane, but also a dangerously dumb human being. 😳👇 https://t.co/DYUyxA4Xq3

🚨 In 2 weeks, a final decision on amendments to the EU AI Act and the GDPR will be made. What is at stake is nothing other than the future of Europe. Many don't know, but the stream of events leading to this moment began much earlier, with the publication of the Draghi report on European competitiveness in September 2024. In his long report, Mario Draghi diagnosed various areas in which European competitiveness was lagging behind and suggested that one of the reasons was overregulation and the excessive number of laws governing the digital space. Laws such as the GDPR and the AI Act were to blame. Before I continue, here is something many overlook: the Draghi report was finalized in September 2024, while the AI Act was officially enacted one month earlier. The AI Act had barely been enacted, and it was already considered 'wrong,' excessive, and to blame for Europe's less-than-ideal (to be light) position in the AI race. From that moment on, the European discourse on the protection of fundamental rights was never the same. Its narrative shifted, and after that, the new dogma was that the path to innovation would be to "remove the red tape," and "apply the AI Act in a business-friendly way." (whatever that means from a legal perspective). The AI Action Summit last year made this new narrative loud and clear to the public, as EU officials abandoned fundamental rights-focused statements. Last year, the narrative shift was legally materialized. The EU published the Digital Omnibus with proposed amendments to some of its most important laws regulating data protection and AI: the GDPR and the AI Act. Strangely, the main justification for the AI Act's amendments was the designation delays by EU member states and the work delays by EU standardization organizations. If these were the real reasons, wouldn't it be more coherent to pressure them to move faster, hire more people, increase the budget, or help address the bureaucratic obstacles...? Does the EU need to amend some of the AI Act’s core obligations because EU bodies are delayed? I didn't buy it. Given the context, it felt more like a broader political shift. The time has arrived, and in two weeks, EU officials will meet to make a final decision on the Digital Omnibus and the amendments to the GDPR and the AI Act (among other topics). As I wrote in my newsletter, several of the proposed amendments weaken AI regulation in the EU and go against the protection of fundamental rights. If you are European, if you were hopeful for a Brussels Effect in AI, or if you are interested in the protection of fundamental rights, I invite you to read my full article below. - 👉 To learn more: - Read my article about the Digital Ominibus first draft and join my newsletter's 93,500+ subscribers (link below). - Join the 29th cohort of my Advanced AI Governance Training. Among the topics I cover in depth are the EU AI Act, the Digital Omnibus, and the European AI strategy (link below).

the economic collapse of gen z in four charts https://t.co/FoWNscQFPh

the economic collapse of gen z in four charts https://t.co/FoWNscQFPh

I love Twitter's new custom feed I just wish it wouldn't reset all the time to the default For You whenever I re-open the app. https://t.co/1U1zJubzK8

Day 7 of Building AGI for my Hermes Agent: I got my GPT-5.4 calls from 270x to 0x per day Today I found one of the dumbest parts of my setup where routine agent work was quietly burning GPT-5.4 token credits. Scanning, summaries, low-risk review, background thinking. These should not be hitting GPT-5.4. So I rebuilt the stack. Using @leopardracer’s Mac Mini local model setup, I got Local Qwen 35B A3B running for the always-on cognitive work as a test. Now the system works like this: - Local Qwen 35B A3B for scanning, summaries, low-risk review, and constant background thinking - MiniMax M2.7 for approved coding work - GPT-5.4 for final planning and high-judgment approval - No model for preflight checks when queues are empty The result: - GPT-5.4 cron calls per day went from 270 to 0. - Now GPT-5.4 only fires when there is real planning work or a deliberate escalation. Frontier intelligence is too expensive to waste on routine cognition, and my system got dramatically cheaper overnight, and much cleaner too. A lot of people are overspending because they are using the smartest model for the wrong jobs. Not every thought deserves a frontier token. Follow @gkisokay to see what happens next.