@TheProjectUnity There is a tunnel still unexplored btw. Apparently it was unsafe to explore(water and earth movement), I went in 2019 and this was what I was told by a local. Also did you go into the museum? Lots of intresting artifacts in there.
If you are reading this, the only possible resistance is to build decentralized, permissionless, and sovereign AI.
Open source, self-hosting tools, RL post-training, local inference, open harnesses, we must build it all.
We must fight overcentralization with an open stack.
Scattered information in. Verifiable agent action out.
OriginTrail gives AI agents a Shared Context Graph to act on — and every answer, transaction, and autonomous decision leaves a verifiable decision trace.
Two commands to plug in your AI agents:
🔌https://t.co/ezTB3Ic1uG
@superalesha Just a next step up improvement I think. Could be a flop but I doubt it.
This will just keep happening. Unreal we are experiencing this chapter of humanity.
Just like @NousResearch Hermes agent grows with you, @umanitek Agent Blackbox keeps growing in the capacity to keep all your agents safe.
Try it out and stay tuned for the new updates dropping this week, including the unlocking of community graph powered by @origin_trail.
@matheushorst@sudoingX Yep I have it loaded on my 1070 works well. Though its a bit slower when run through hermes. Im using 64k context. 6g of 8g being used. Haven't bumped it up to 120k yet.
AI agents just got their own security perimeter.
Agent Blackbox helps detect prompt injections, leaked keys, malicious packages, and dangerous commands before they cause damage.
Install it with one command and protect your agents today 👇
Bots already outnumber humans online. Deepfakes and impersonators are coming for everyone.
@umanitek showcased the Guardian agent walkthrough:
• Real-time detection of fake impersonator accounts across X, TikTok, IG for world-class athlete Neymar
• Paste any URL → instant forensic Evidence Pack and takedowns (via dashboard, WhatsApp or Telegram)
• TrueSeal deepfake scanner that spits out verifiable certificates (e.g. 93% fake on that injury pic)
• “Make it go away” button + agent-assisted takedowns with 90%+ success rate
All running on @origin_trail DKG so the AI actually knows what’s true and can act.
This is how we fight back in the age of agentic AI.