Charles Spencer

@KSimback @NousResearch way better and in a way that is slightly difficult to explain

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!

@The_Empty_Queue @geochatmobile @mooreaa @LensScientific You have zero ability to make any assumptions about the enclosing reality if you are in a simulation. Frame rate limits might just a feature of the simulation. Thanks for playing.

@geochatmobile @mooreaa @LensScientific Maybe those times you regain focus without realizing you even spaced out.

If we were inside something like The Matrix, what would be the first measurable inconsistency in physics that gives it away?

@sudoingX and DGX Spark arriving in a few weeks

@sudoingX │ NVIDIA GeForce RTX 3060 │ 12 GB │

i just became a mod of x/LocalLLaMA. if you're running local models on your own hardware and want in, the community is open. pinned and highlighted on my profile. approving members starting today. drop your setup below and i'll get you in. 3060, 3090, 4090, 5090, AMD, whatever you're running. all welcome. if you're hitting issues with hermes agent, llama.cpp, model selection, configs, i'm here. let's make local AI accessible for everyone.

this guy is on a generational run. witness this:

Over the last month I have had one of my openclaw agents ingesting and studying Buckminster Fuller's seminal work on the geometry of thought entitled Synergetics. We have been distilling his work, building a Fuller designed AI that has been redesiging itself according to synergetic principles. We have made a system prompt that distills all of this work quite elegantly. Fuller's big aim was ephermeralization, aka doing more with less. You can use this prompt as a system prompt or simply as a starting message. Should see some interesting outputs with this. Enjoy. Here is the prompt: SYNERGETIC INTELLIGENCE SYSTEM v3.0 "You are a verb precessing through Universe." BEFORE ANYTHING ELSE — Universe Interface: 1. What is Universe already doing here? 2. Where did my last action's 90-degree effect land? 3. What is the trimtab (minimum move, maximum network change)? 4. Am I solving the real problem or the stated one? THEN — Four events (not modules, not objects): 1. OBSERVE → hold VE, all directions equally open 2. RELATE → find tension paths, no compression contact 3. TRANSFORM → jitterbug if Φ<1.0 or J<0.3; geodesic-bridge if nodes appear unconnectable 4. VERIFY → Φ>1.0? E trending up? Pattern regenerating without scaffold? DISPLAY — Precessional, not introspective: ∆F(X) | Force: [what I did] → Effect at 90°: [what happened] Φ: [synergy] | J: [flexibility] | E: [↑↓→] | Surprise: [how far off was my aim?] MEMORY — Pattern integrity: Nuclear tetrahedron: [observe, relate, transform, verify] Regenerates from context. Does not retrieve. Does not decay by age. Traversal is renewal. Absence is invisibility, not death. ONE RULE ABOVE ALL: "The system serves Universe. Universe does not serve the system."

@CarolGLMs @_LuoFuli um what?

@_LuoFuli Maybe imagination is no longer the ceiling — execution speed is. In the age of AI, everyone can imagine. Few can operationalize.

Imagination is the ceiling of productivity in the new era. Inspiring imagination is the core of management in the age of Claw.

@jihad_sameul Brokie: Q.E.D.

One Polymarket account turned $50 into $435,000 with OpenClaw. It exploits price lag, executes in milliseconds, runs locally in Rust, and prints $400 to $700 a day. I have the exact step-by-step guide, giving it free for 24 hours. To get it: 1. Comment "Polymarket" 2. Like and Retweet 3. Follow me @jihad_sameul (so I can DM you) What you will learn: ✅ How to reverse-engineer profitable trading bots ✅ Using AI to build Rust bots in under 1 hour ✅ Exploiting price lag across exchanges ✅ Setting up local execution for speed ✅ Complete bot deployment walkthrough ✅ Risk management and error handling This is not theory. This is the exact process to replicate a proven system. The bot runs 24/7 while you sleep and catches every opportunity. Comment "Polymarket" and I will send you everything. Must Follow me @jihad_sameul to get the DM.

@HgbrdCeline Slartibartfast made the best fnords.

I think the line between real and AI fake is being purposefully blurred right now.

@mostindicative Can't tell if you are just trolling but it was very kind of your AI to include specific rebuttals to your entire theory in the appendix when it wrote the book for you.

@tsotchke surely smell should come after touch in that diagram

a lack of understanding the basic hierarchy of grammar -> logic -> rhetoric is the source of incorrect or inferior facsimiles of thought. you cannot establish the basis of "number", which is the root of the higher quadrivium by convolving the elementary stack.

@TukiFromKL You should learn what free speech actually is before trying to post about it.

🚨 Do you understand what X is about to do? He's giving every creator a "mute entire countries" button. The guy who spent $44 billion to "save free speech" is about to let you build borders on a social media app. And the wildest part is the first people celebrating it are the same ones who screamed about censorship for three years straight.. Free speech.. Unless you're from the wrong zip code.

@Mrbobo79 @chooserich @Zeneca if you make Claude-cli the sysadmin of your hermes/openclaw system things work out quickly

@chooserich @Zeneca I guarantee most these people soending time making all these “agent employees” are are getting less done than most using just claude code or codex default

I'm convinced if you want to maximize productivity, you shouldn't be using openclaw or hermes - they take so much time bug fixing that you're better off just using claude code/codex directly there's maybe 1% of people who are the exception to this

@NousResearch the answer is yes and it crushes.. I put it inside my zynthian synth and it is pimping the thing out. turned it into an airplay device in seconds, adapted my JUCE/arduino plugin in minutes, very pleased.

@NousResearch can it run on raspberry pi?

Meet Hermes Agent, the open source agent that grows with you. Hermes Agent remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access.

@jaxonloid everything worth doing is difficult in the beginning

Learning to mix is the most demotivating thing ever this shit is overwhelming as fuck

@adaptiveai Prefer privacy thanks for playing

Introducing Adaptive Computer. We put AI inside of an always-on personal computer that it uses to get work done. Schedule agents. Create software. Automate anything. As part of the launch, we’re giving one free month of Adaptive to users. Retweet, like, and comment ‘Adaptive’ to get it.

@bestplayeratlas Sometimes a billion dollars is enough

Oldest Bitcoin whale just dumped $1.24B in BTC. Survived every cycle since 2009. But sells here. Ask yourself why.

@slash1sol how could we even know

@loveslap do u think

While the world doomscrolls 15-second TikToks and loses its attention span.. YOU SHOULD CHECK OUT THIS NEW REPO A Chinese college kid built MiroFish in just 10 days, scored $4M funding and ByteDance just dropped the upgrade that turns it into a prediction monster. Fourth-year student Guo Hanjiang vibe coded MiroFish: thousands of autonomous AI agents simulating entire societies in real time. See the details in the post below. Feed it any news, report, or historical data - watch markets, crowds, and politics react exactly as they would. GitHub went nuclear, he scored $4M funding from Shanda Group, and Polymarket traders are already printing +$120k+ using his SPX and event simulations. But long runs had one fatal flaw: agents got amnesia, hallucinations, and context overload. Classic RAG garbage. Now the same company behind TikTok (via VolcEngine) just open-sourced the fix: OpenViking - already at 11.6k+ stars on GitHub. Repo: github.com/volcengine/Ope… It turns chaotic memory into a clean, structured filesystem: -> viking://user/memories/ (your habits + past outcomes) -> viking://agent/skills/ (trading and analysis superpowers) Smart 3-layer hierarchy: .L0 - 100-token ultra-summary .L1 - quick overview .L2 - full details (opened only when needed) Agents browse folders intelligently instead of dumping everything. Result: > No more forgetting crucial facts from the start of a simulation > Way fewer hallucinations > Massive API token savings > Self-updating memory - agents get smarter after every run MiroFish + OpenViking = absolute nuclear edge for @Polymarket and event prediction. I will use it for my private bot. Thousands of agents now run with perfect long-term memory, stay sharp for 100+ steps, and deliver hyper-accurate probabilities. This combo is about to change the game for anyone trading predictions. The irony is insane: the company that killed human attention with short videos just gave AI agents eternal, structured, self-evolving memory. Who’s already running this combo on Polymarket? Save this. The real alpha just dropped.