Marie Haynes

I love learning and sharing about AI. Formerly a veterinarian, in 2008, understanding Google search algorithms captivated me. In 2022 my focus shifted to understanding AI. AI is the future!

Explore
Image of: New Google Research on reducing hallucinations in LLMs that use RAG New Google Research on reducing hallucinations in LLMs that use RAG

New Google Research on reducing hallucinations in LLMs that use RAG

By Marie Haynes
Research, Gemini, ChatGPT

This is an interesting Google Research Paper, published in December 2024. The methods introduced here reduced hallucination rates when using Retrieval Augmented Generation (RAG) in models like Gemini and GPT by 2-10%...

Image of: Training Language Models to Self-Correct via Reinforcement Learning - DeepMind paper Training Language Models to Self-Correct via Reinforcement Learning - DeepMind paper

Training Language Models to Self-Correct via Reinforcement Learning - DeepMind paper

By Marie Haynes
Research, DeepMind, Google

Google DeepMind's SCoRe method uses reinforcement learning to train language models to effectively self-correct through iterative revision, significantly improving their accuracy and reliability....

Image of: Gemini’s Deep Research may make many affiliate sites unnecessary Gemini’s Deep Research may make many affiliate sites unnecessary

Gemini’s Deep Research may make many affiliate sites unnecessary

By Marie Haynes
Search, Agents, AI Overviews, Google

Gemini's new Deep Research is an early example of an AI agent. I think it is something that will radically change how people search. I have found it extremely helpful already. But I do worry that this feature will be bad news for many websites, especially affiliate sites....