Lawyers will never eliminate AI hallucinations with today’s technology. But they can reduce them—sometimes substantially.
Hallucinations arise from fundamental characteristics of current large language models, which generate answers by predicting plausible language rather than independently determining whether every statement is true. Recent OpenAI research adds another wrinkle: AI systems can be rewarded for guessing rather
The marketing promise for premium legal RAG-based models was a hallucination-free experience. The empirical reality is different. Why?
It is a structural problem, created by the way Large Language Models are created. The process includes inputting large amounts of information. This typically includes all the publicly available information on the Internet.
The next step is
There’s lots of big talk about the best approach to improving access to justice for self-represented litigants. Dennis Kennedy is not big on theory and bloviation. His most recent article on this topic is available for free republishing in favor of cheap, practical, and effective approaches.
Dennis ran several prompts below through Gemini, with good
In the Kennedy-Mighell Report Episode 300, What’s Happening in LegalTech Other than AI? Dennis Kennedy and Tom Mighell had some good ideas in response to my recent question about where to find prompt libraries. It’s good to have starting points, but I strongly agree with Dennis that “roll your own” is the way to go.
Two plain-language ChatGPT prompts designed specifically for lawyers. They uncover gaps, sharpen your visibility, and provide clear next steps
The best way to learn to use AI effectively is to let AI help you.
Continue Reading Using AI to Use AI Better