We will reward you for going Erli. We focus on Blockchain, Biotechnology, Neuro-Linguistic Programing, AI/ML/Expert Systems, Web3 Games, Cyber. Closed-Source.
e/acc tip:
Stay up to date with how Decel's are trying to hack LLM's. There is a lot of good innovation there for positive actors to understand.
LLM Hacking: Prompt Injection Techniques
medium.com/@austin-stubbs/ll…#HumanNotHuman
e/acc tip:
Design your models so that you can ask it questions once finished tasks, or as the model(s) are being trained, and or during model run.
It feels good asking an AI why is choose to do the thing that is did to achieve it's objective. The responses are incredible!
An AI experiment that used AI agent(s*) to engage with others through many social media channels. The agents were able to build personas, narratives, and skirt may of the content ranking algorithms without human intervention.
is this useful research?
The next step is to provide interactive audio and video replays of their mission.
next, prompt the collective agents and ask questions with respect to the solo agent as well as the collective strategy(logs, blockchain transactions, etc).
#blockchainAI#dpin#humanNotHuman
Today we are conducting preliminary ElectroMagnetic Compatibility (EMC) testing of @SomniumSpace#VR1 headset 🔥👏
Full version (ET HT MR).
We are getting much closer to release!
Go team!
e/acc notice:
"But one of the big reasons for the standoff at OpenAI is that everyone involved thinks a new world is not just coming, but coming fast."
@scottmelker