ısıɹɐd ןǝɐɥɔıɯ

You’ve billed my next month @ollama — so when does my usage actually reset?!

Hey @ollama how about another random session reset? Trying out GLM 5.1 absolutely wiped me out! :-(

we all deadname twitter right?

@browser_use @NousResearch This got flagged as medium warning level. No thank you.

We just gave every Hermes Agent a free cloud browser. Use the Browser Use ecosystem in Hermes Agent for free > Unlimited browser hours > Free proxies > Persistent authentication @NousResearch 🤝 Browser Use

@Thebestfigen Wouldn’t you see a dead corpse floating in space?

Paradox: If you see a baby located 90 light-years from Earth, right now it would be a 90-year-old, but you see it in your present, as a baby. While the light takes time to reach you, the baby grows and ages. When you look at the universe, you are always looking at the past.

Okay so "Cirie's Rizard Of Oz" is the best alliance name of all time right? #Survivor50 @SnuffinTorches

@kevinnguyendn @NousResearch @karpathy @ollama Thank you.

@MichaelParisi @NousResearch @karpathy @ollama Read more: docs.byterover.dev/external-llm-p…

ByteRover is now live in the Hermes Agent memory update @NousResearch One minute setup: just run hermes memory setup and your agent gets memory. Fully open-source & local, no cloud API keys. Built on native markdown architecture (validated by @karpathy), but we automated the entire curation (management) layer so memory actually scales with your projects. Prompt as usual, and the agent will recall the exact knowledge and historical decisions. Proven in real production with teams. Optimized for accuracy, latency & token reduction.

“/btw” actually works with @ollama powering @openclaw now. But thanks for all those responses when it was returning errors, guys!! 🙄

@kevinnguyendn @NousResearch @karpathy Ok, well then where do I go to get it? And can I use it with the @ollama I’m already using as my LLM?

@MichaelParisi @NousResearch @karpathy ByteRover itself is fully local, The LLM API key prompt is for the LLM provider that uses to power the agent (OpenAI, Anthropic, etc.). The memory system runs on pure markdown + local compute, but the agent still needs an LLM to think with.

Lend me $10,000 but only give me $5,000. That way you owe me $5,000 and I owe you $5,000 and we can just call it even.

I'll never stop calling this app "Twitter"

I really mean it when i say i don't eat at Chick-fil-A. Nothing tastes as good as standing up for what you believe in.

@huntharo @telegram @openclaw What’s the bot’s peer ID? How do we get that? Is that just the part of their token before the “:”?

It looks like my @telegram iOS PR has been deployed (or something similar). Now you can talk to your @openclaw via Siri / CarPlay on iOS. 1. Create an iOS Contact for "Claw" (or any name) 2. Add a URL field with name `Telegram` and value `@id12345" target="_blank" rel="nofollow noopener">t.me/@id12345` where 12345 is your bot's peer id 3. "Hey Siri, message Claw on Telegram" now works! Note that you have to have an open chat with your bot already and you cannot accidentally start chatting with random bots with this design.

@cathrynlavery THANK YOU!!!!!!

🦞 Openclaw update fix If your agents are hitting exec approval walls after the latest update, the fix is three settings: In exec-approvals.json defaults: - security: "full" - ask: "off" - askFallback: "full" In openclaw.json: - tools.exec.security: "full" - tools.exec.strictInlineEval: "false" Then restart gateway. The allowlist wildcard * alone isn't enough. There's a second policy layer that gates complex commands independently.

This is so cringe! @Applebees is “the biggest reward of “Survivor#50”?!?! UGH Seriously?! THAT’S the best they had?

Why does the person in front of me always gotta take speed bumps like they have a fucking wedding cake or Jenga set up in their back seat?! UGH!!!

@ollama Does v 0.18.2 fix the “/btw” error 500 issue in OpenClaw?

@steipete I keep getting 500 errors when using "/btw". Also the web ui dashboard at localhost:18789 hasn’t shown reasoning or chat updates without a refresh for a few updates now. Are these known bugs, or just an @ollama issue?

🤣🤣🤣