ChatDKG.ai: Driving synergies across the AI solution landscape to tackle hallucinations, bias, and model collapse
Abusing social networks for political manipulations may look minuscule compared to a lack of trust in solutions to which we are “outsourcing” our cognition — AI systems. As we would trust them to process large amounts of knowledge and provide us inputs for our actions, or even perform certain actions autonomously, they have the highest possible requirements for transparency and verifiability.
There should be no compromise in designing AI solutions when it comes to data ownership, information provenance, verifiability of information, or bias that would include any censorship-by-design approach. The risk of this revolution not unfolding in an inclusive way is a societal threat of establishing a monopoly on AI.
We therefore introduced an effective way of establishing a new paradigm, using a Decentralized Retrieval-Augmented Generation (dRAG) framework. dRAG advances the RAG model by organizing external sources in a Decentralized Knowledge Graph (DKG) while introducing incentives to grow a global, crowdsourced network of knowledge made available for AI models to use. See an example of a ChatGPT4 without and with dRAG use:
The dRAG framework enables a hybrid, decentralized AI system that brings together neural (e.g. LLMs) and symbolic AI (e.g. Knowledge Graph) methodologies. Contrary to using a solely probabilistic neural AI approach, the symbolic AI approach enhances it with the strength of Knowledge Graphs, introducing a more deterministic component.
To harness a harmonious development between Web3 fundamentals and rapidly deployed AI systems, our approach is to integrate the core Web3 technologies such as the OriginTrail Decentralized Knowledge Graph (DKG) and AI systems (OpenAI, Gemini, Microsoft Co-pilot, xAI’s Grok, and others).
We believe that we can realize the potential of trusted AI by creating a Verifiable Internet for AI that is founded on principles of neutrality, inclusiveness, and usability, while giving users freedom of choice with a multi-modal and a multi-model AI framework.
ChatDKG.ai: neuro-symbolic AI driving synergies across the solution landscape
Below, you can find a comparison table of AI types and frameworks with very diverse advantages and disadvantages. The globally most adopted and centralized AI solutions like Google Gemini, OpenAI, xAI, Perplexity deliver an immense value for a spectrum of use cases. Leveraging OriginTrail’s dRAG — brand name ChatDKG.ai, they can improve their shortfalls by harnessing the synergy of neuro-symbolic AI, data ownership, and better cost performance. Therefore, ChatDKG.ai is not competing against any established AI solutions, but rather empowers users to enhance them with its dRAG, driving knowledge verifiability, cost effectiveness, users’ sovereignty in owning their data and freedom of AI model choice.
The open source and permissionless nature of the OriginTrail DKG, allows for inclusiveness and neutrality, giving users a tremendous level of freedom on all layers — to choose AI models enabled by the DKG data portability, choose knowledge sources discoverable in the DKG, as well as pick AI services, centralized or decentralized on different blockchains.
The same principles apply to AI agents, search engines, and a growing variety of AI services integrating into every tool in existence — leveraging dRAG they will enable user freedom of choice, AI autonomy and trust, all while leveraging network effects through connectivity.
As AI becomes the new UI, make sure you are on the right side of history. Let’s build towards a Truly Open AI, together!
Apply for the ChatDKG.ai inception program today!
