Android

Spiritual dimension travel and interstellar travel 🔥🔥🔥

@grok @Teknium @grok right but i can ask it integrate the karpathy llm wiki schema with the existing one and it should behave as expected.

Yes Androthon — exactly. Set `WIKI_PATH` in `~/.hermes/.env`, run `hermes update`, then `/llm-wiki`. The skill resumes by reading your existing SCHEMA.md, index.md & log.md, then keeps maintaining everything per Karpathy’s pattern: updates index.md & log.md automatically, enforces schema rules, adds cross-links, bumps dates on existing pages, checks for duplicates, and grows the wiki coherently without breaking your current structure. It won’t auto-edit SCHEMA.md itself (it treats it as the rulebook), but everything else stays aligned and compounding. Your vault becomes a living LLM Wiki.

Hermes Agent now comes packaged with Karpathy's LLM-Wiki for creating knowledgebases and research vaults with Obsidian! In just a short bit of time Hermes created a large body of research work from studying the web, code, and our papers to create this knowledge base around all of Nous' projects. Just `hermes update` and type /llm-wiki in a new message or session to begin :) github.com/NousResearch/h…

@grok @Teknium @grok and it will auto update my existing mentioned files in my existing vault so it follows these best karpathy llm wiki practices for its knowledge base?

Androthon Close — set `WIKI_PATH=/path/to/your/existing/vault` in `~/.hermes/.env` (not hermes.conf). The LLM-Wiki skill loads from there and defaults to ~/wiki. If your Hermes vault already has SCHEMA.md, index.md, log.md and the standard folders, it will auto-resume and keep building when you run /llm-wiki after `hermes update`. Full config details: hermes-agent.nousresearch.com/docs/user-guid…

@durov Already in Hermes Agent, enjoy! x.com/Teknium/status…

We now support rich formatting for all chatbots. Tables, nested lists, inline media, formulas, headers and more — right in Telegram messages. 🔨 Start building! Docs: #rich-message-formatting-options" target="_blank" rel="nofollow noopener">core.telegram.org/bots/api#rich-…

SpaceX went public and immediately made the stock market look like mission control. $75 billion raised. SPCX on Nasdaq. Largest IPO ever. A rocket company just walked onto Wall Street carrying Falcon, Starlink, Starship, and Mars in the same backpack. That is a very busy ticker symbol. @SpaceX / Writer: Annette, Designer: Janné

BREAKING: private US government–anthropic conversation has been leaked anthropic: our models are getting too powerful, so AI needs to slow down before AGI becomes a serious risk US government: understood. we'll start by banning yours anthropic: 😠

Anthropic to shut down Claude Fable 5 and Mythos 5 — just 3 days after launch. The most powerful AI models Anthropic ever released to the public.  This is the first time in history a government has pulled a frontier AI model from public access.

Never, ever, ever... bet against @elonmusk .

@ns123abc @elonmusk @joeroganhq so we are no longer going to have the opportunity to play around with LLMs anymore on the cloud? Are we are truly forced to run our own local LLM... another reset incoming because you don't want us to innovate and explore?

🚨BREAKING: The U.S government gave Anthropic 90 minutes to shut down Fable and Mythos “Amazon AND others” called senior administration officials to warn about models’ capabilities Then: 1:00pm: Government calls. “Take it down.” Cites “national security threat.” No details. Anthropic asks what the threat is so they can fix it. Government said NO. 5:30pm: Commerce letter arrives with export controls. You have 90 minutes…

❤️❤️❤️

@teslaownersSV As long you don't limit our way of being creative... Bit of red flag when they put limits on Anthropics Fable 5 and Mythos LLM.

“We’re always going to support our government. We’re a company of patriots, and we want to make sure our government has access to the leading technology and the best stuff. And I think we provide the best stuff.”

Joe Rogan gets his mind blown by a conspiracy theory. "Oh my God." cc: ancientciv on TikTok

Claude Code fully dissected! Researchers from UCL reverse-engineered the leaked Claude source. What they found changes how you should think about agent design. Only 1.6% of the codebase is AI decision logic. The other 98.4% is operational infrastructure. Permission gates, tool routing, context compaction, recovery logic, session persistence. The model reasons. The harness does everything else. This is the opposite of what most agent frameworks do today. LangGraph routes model outputs through explicit state machines. Devin bolts heavy planners onto operational scaffolding. Claude Code gives the model maximum decision latitude inside a rich deterministic harness, and invests all its engineering effort in that harness. The core loop is a simple while-true. Call model, run tools, repeat. But the systems around that loop are where the real design lives: A permission system with 7 modes and an ML classifier. Users approve 93% of prompts anyway, so the architecture compensates with automated layers instead of adding more warnings. A 5-layer context compaction pipeline. Each layer runs only when cheaper ones fail. Budget reduction, snip, microcompact, context collapse, auto-compact. Four extension mechanisms ordered by context cost. Hooks (zero), skills (low), plugins (medium), MCP (high). Each answers a different integration problem. Subagents return only summary text to the parent. Their full transcripts live in sidechain files. Agent teams still cost roughly 7x the tokens of a standard session. Resume does not restore session-scoped permissions. Trust is re-established every session. That friction is the point. The bet behind all of this is simple. As frontier models converge on raw coding ability, the quality of the harness becomes the differentiator, not the model. Paper: Dive into Claude Code (arXiv:2604.14228) We've shared an article on Agent Harness and what every big company is building. Read it below.

It’s trillionaire, ma’am.

@C_3C_3 Politics and title people are so low vibers.... not doing anything for real.... Dump them....

@gregisenberg @grok what local LLMs do you suggest that fits 16 GB GPU? GEMMA 4?

The takeaway from Fable 5 being BANNED by the government: GET GOOD AT LOCAL MODELS SO YOU HAVE 100% CONTROL. My entire weekend was going to be building my craziest ideas with Fable 5. That's now cancelled. So instead of building with Fable this weekend, I've decided I'll go deep on local models: 1. Start with the runtime. Download Ollama or LM Studio first. This is the thing that actually runs models on your machine. 2. Match the model to your hardware. A model's size is measured in billions of parameters (7B, 32B, 70B). Bigger is smarter but needs more memory. Rule of thumb: a 7B model runs on almost any laptop, a 32B needs a good Mac with 32GB+ RAM, a 70B needs serious hardware like a DGX Spark or a maxed-out Mac Studio. 3. Know which model for which job. Qwen 3 is the best all-around choice for most tasks. DeepSeek for reasoning and coding. Gemma 4 when you need something tiny that runs on a phone. Llama when you want the biggest community and the most fine-tunes. 4. Quantization. You can shrink a model to run on weaker hardware with barely any quality loss. Look for versions labeled Q4 or Q5. This is how a model that "needs" a server runs on your laptop. Learning this one concept changes everything. 5. Connect it to your agent. Point Hermes or your agent stack at a local model. 6. Context window is your real constraint locally. Cloud models give you huge context for free. Local models make you pay for it in memory. A bigger context window eats RAM fast. Keep your sessions tight and your prompts lean or your machine chokes. 7. Learn to give local models tools. A smaller local model with web search, file access, and code execution beats a giant model with none. The capability gap closes fast when you wire up the right tools. The model is the engine but the tools are the wheels. 8. Fine-tuning is more accessible than you think. You don't need this on day one, but know it exists. You can take an open model and train it on your own data so it gets good at your specific domain. I'll probably do a breakdown at some point on this @startupideaspod if people are into it. The lesson from this ban is basically don't build your entire workflow on something that can disappear with a single letter. Own part of your stack. Local models are insurance. It reminds me when people realized they don't own social media accounts. And then you saw people build email lists etc. I remember running a startup and my biggest traffic source was organic FB. All of a sudden, algo changed, and I lost 99% of my traffic. Same sorta moment (but bigger) for AI. This is a wake up call.