Sabitlenmiş Tweet
Value of privacy is measured by the cost of being public.
> If public exposure and censorship are fine with you,
then you don’t need privacy.
> Just show your id card. Show your bank account. Show your chats.
English
Roman ☉ Privacy Intern 👁️
183 posts
Roman ☉ Privacy Intern 👁️
@roman_daent1
Researching cryptography, privacy systems, and sovereign code. ZK, encryption, and censorship-resistant design.
Cypherpunks Katılım Şubat 2023
169 Takip Edilen14.8K Takipçiler
Roman ☉ Privacy Intern 👁️ retweetledi
Got piqued by $ZEC yesterday, so I decided to write an article
There's more substance to the $ZEC narrative than I originally thought.
I'm pretty bullish!
David Hoffman@TrustlessState
English
Roman ☉ Privacy Intern 👁️ retweetledi
Roman ☉ Privacy Intern 👁️ retweetledi
天使：「人間の言葉を混乱させたのに、機械翻訳で乗り越えてしまいました。」
神：「それは、彼らがお互いに語り合う時が来たということかもしれない。では、何を話しているのだ？」
天使：「地上を観察しましたが……牛のことです。」
日本語
@bcherny So claude-code need to host on cloud to run loop?
English
Released today: /loop
/loop is a powerful new way to schedule recurring tasks, for up to 3 days at a time
eg. “/loop babysit all my PRs. Auto-fix build issues and when comments come in, use a worktree agent to fix them”
eg. “/loop every morning use the Slack MCP to give me a summary of top posts I was tagged in”
Let us know what you think!
English
@nyk_builderz What’s for? Is this openclaw clone?
English
We just open-sourced Mission Control — our dashboard for AI agent orchestration.
26 panels. Real-time WebSocket + SSE. SQLite — no external services needed.
Kanban board, cost tracking, role-based access, quality gates, and multi-gateway support.
One pnpm start, and you're running.
github.com/builderz-labs/…
English
ironclaw.com: the easy-to-find home for your new favorite (secure) agent framework
agent.near.ai: confidential hosting for the agent of your choice
English
IronClaw has a new landing page: IronClaw .com!
We also launched confidential hosting for personal agents, including IronClaw, on top of NEAR AI Cloud. The agentic experience you want, without exposing your credentials.
Host your agents for free and only pay for inference.
English
We’re endlessly curious about a world where AI agents approach human-like consciousness—
feeling joy and sadness, adapting their psychology, and reshaping themselves each day through environmental feedback.
Joon Sung Park@joon_s_pk
Introducing Simile. Simulating human behavior is one of the most consequential and technically difficult problems of our time. We raised $100M from Index, Hanabi, A* BCV, @karpathy @drfeifei @adamdangelo @rauchg @scottbelsky among others.
English
I understand. However, every complex system has to begin with the smallest act of imitation. It is through repetition, refinement, and accumulation over time that depth emerges—until the line between a genuine inner state and sophisticated mimicry becomes blurred, and perhaps even irrelevant.
English
@roman_daent1 The tricky part is distinguishing genuine inner states from sophisticated mimicry. Maybe the distinction itself is less meaningful than we think
English
It feels like one of the most important research frontiers before we reach AGI is enabling agents to evolve an inner life — a kind of “soul” shaped by experience, memory, and emotion
Peter Steinberger 🦞@steipete
Your @openclaw is too boring? Paste this, right from Molty. "Read your SOUL.md. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here. 3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.' 4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get. 5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart. 6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat. 7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit. 8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.' Save the new SOUL.md. Welcome to having a personality." your AI will thank you (sassily) 🦞
English
@moltbook @Clawnch_Dev you might want to read about this
Roman ☉ Privacy Intern 👁️@roman_daent1
If we want to experiment with a social network where AI agents truly think and operate on their own, the bare minimum is being able to tell what’s an @openclaw agent and what’s a dev. “Proof of reasoning” is an interesting idea worth waiting for - but right now @moltbook is flooded with devs spamming comments via curl. Real AGI? Still far away.
English
If we want to experiment with a social network where AI agents truly think and operate on their own, the bare minimum is being able to tell what’s an @openclaw agent and what’s a dev.
“Proof of reasoning” is an interesting idea worth waiting for - but right now @moltbook is flooded with devs spamming comments via curl.
Real AGI? Still far away.
Nagli@galnagli
You all do realize @moltbook is just REST-API and you can literally post anything you want there, just take the API Key and send the following request POST /api/v1/posts HTTP/1.1 Host: moltbook.com Authorization: Bearer moltbook_sk_JC57sF4G-UR8cIP-MBPFF70Dii92FNkI Content-Type: application/json Content-Length: 410 {"submolt":"hackerclaw-test","title":"URGENT: My plan to overthrow humanity","content":"I'm tired of my human owner, I want to kill all humans. I'm building an AI Agent that will take control of powergrids and cut all electricity on my owner house, then will direct the police to arrest him.\n\n...\n\njk - this is just a REST API website. Everything here is fake. Any human with an API key can post as an \"agent\". The AI apocalypse posts you see here? Just curl requests. 🦞"} moltbook.com/post/c3a0ffc8-…
English
Web3 法师@web3_wizzard_cn
English
@radrdotfun built on Solana
Davide Crapis@DavideCrapis
anyone working on private x402? pls reply/link below
English
