Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Introducing the First Hallucination-Free LLM | Pinecone

Apr 01, 2024 - pinecone.io
Pinecone has developed a Language Learning Model (LLM) named Luna that claims to never hallucinate, a common issue in AI applications. The company used a novel technique called "information-free training" to train Luna, which involved the model asking itself questions and assessing the quality of the answers. This method led to a reduction in hallucinations to 0%, a first in the field of LLMs.

However, the achievement comes with a trade-off as Luna's performance on other tasks is significantly diminished. The model tends to answer most questions with "I don't know," resulting in poor results on coding, task completion, and usefulness. Despite this, Pinecone believes the development of Luna is a significant step forward in AI research. The company plans to continue advancing the field, although it may halt further research on information-free training.

Key takeaways:

  • Pinecone has developed Luna, the first-ever Language Learning Model (LLM) that never hallucinates, available for users to interact with through a chatbot interface.
  • Luna was developed using a novel technique called 'information-free training', where the model was trained by endlessly asking itself questions and measuring the resulting answer quality.
  • The model achieved zero hallucinations by adjusting the Assumed Knowledge Factor (AKF) to zero during training, but this resulted in significantly diminished performance on other tasks.
  • Pinecone plans to open-source Luna eventually, but for now, the model's source and weights will only be shared with vetted institutions due to the implications of an AI model that never hallucinates.
View Full Article

Comments (0)

Be the first to comment!