We've published a new whitepaper for Aurelius, a decentralized protocol designed to generate alignment training data under a completely new data paradigm, one that proposes alignment as an emergent property of multi-agent systems. The protocol operates as Subnet 37 on Bittensor, where independent participants compete to evolve alignment environments and...
We’ve just published the first whitepaper for Aurelius, a decentralized protocol designed to generate verifiable alignment data through adversarial prompting, reasoning transparency, and contestable evaluation. The system draws from cryptoeconomic design principles (inspired by Bittensor and Bitcoin) but applies them to the AI alignment problem, with interpretability and reasoning coherence...
We've published a new whitepaper for Aurelius, a decentralized protocol designed to generate alignment training data under a completely new data paradigm, one that proposes alignment as an emergent property of multi-agent systems. The protocol operates as Subnet 37 on Bittensor, where independent participants compete to evolve alignment environments and world model capabilities.
From the abstract:
"Alignment in biology emerged as the optimal strategy of the atomic unit; by replicating the foundational selection pressures, aligned intelligence emerges from atomic units of moral reasoning. Aurelius is a decentralized protocol that generates corpora designed to align intelligence through a hybrid data paradigm. Current data is either human-generated and unscalable, or synthetic and fabricated. To bridge the... (read 167 more words →)
Yes you've got the idea framing exactly right.
One clarification: this is not a zero-sum game between miners (prompters) and validators (judges). The validators will reward outputs adhering to whatever criteria the protocol designates as "valuable". The adversarial term mostly refers to miners vs. [misaligned] LLMs.
So this is why I'm here:
What are the "wish list" schema dimensions (miners and validators both) from a research perspective?
What is the best way to aggregate, tag/label, categorize and package this into datasets that researchers can draw meaningful conclusions from?
What is an intelligent way to define and iterate "valuable" outputs (the mechanism itself will be python based script) from miners on the protocol, so that Aurelius becomes an... (read more)
I'm very interested by this premise. I think I should clarify the (Phase I) intent of Aurelius. It is not conceptualized as [a competitive game to surface goodness]. Rather, it can be thought of as an answer to shortcomings in observable overfitting to centralized alignment methodologies like those mentioned in the whitepaper (InstructGPT, CAI, etc). The efficacy of these methodologies is constrained largely due to centralization of prompting and evaluating agents.
Aurelius uses game-theoretic incentives to induce decentralized participants to generate [misalignment] data at scale. We hypothesize this will result in a proliferation of data that may illustrate:
1) the contour of misalignment in a given model (via adversarial probing)
2) how MI and CoT... (read more)
We’ve just published the first whitepaper for Aurelius, a decentralized protocol designed to generate verifiable alignment data through adversarial prompting, reasoning transparency, and contestable evaluation. The system draws from cryptoeconomic design principles (inspired by Bittensor and Bitcoin) but applies them to the AI alignment problem, with interpretability and reasoning coherence as first-class citizens.
At its core, Aurelius is an evolving market for epistemic conflict, where independent agents are rewarded for surfacing misaligned behavior, evaluating reasoning quality, and refining collective judgment over time. The protocol is designed to scale adversarial robustness, not through static judging rules, but through a dynamic, recursive feedback loop.
This version outlines only Phase 1 of the protocol. Future papers will... (read more)
Hello,
I've just joined LessWrong officially today, but I've been staying abreast of the content here and on Alignment Forum for the last few months. I'm extremely interested in AI Alignment research. Specifically I've decided to participate in this community to discuss alignment methodologies and interact with AI alignment researchers at the cutting edge.
Additionally, I've founded a company called Aurelius. (aureliusaligned.ai)
My goal with Aurelius is to explore misalignment in general reasoning models, collect data, and distribute it to researchers and model developers. I'm excited to get feedback on my ideas and participate in ongoing alignment methodologies. I'm based in Los Angeles, and may come to future LessWrong or Alignment Forum meet ups.
Nice to meet you all,
Austin