Walk through and discussion of Legal Prompt Engineering examples, showing ways to compose inputs to generative AI systems like ChatGPT and Claude to get improved outputs for law and legal processes
On this episode of law.MIT.edu's IdeaFlow, guest Damien Riehl joins host Dazza Greenwood to explore the concept of "Legal Prompt Engineering" including an example Damien recently posted showing how a legal brief can be developed in response to a complaint.
Background Materials:
Generative AI & Law materials and video archived sessions from the 2023 MIT Computational Law Workshop: https://law.mit.edu/pub/2023-workshop
Generative AI & Law presentation and blog post materials from CIVICS.com/AI
ChatGPT on Fiduciary Duties: https://www.civics.com/pub/chatgpt-session-2022-12-17
Claude on Fiduciary Duties: https://poe.com/s/XDKWXTP7RDFHbiLvECHP
Prompt Engineering tips from OpenAI: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api
Legal Prompting: Teaching a Language Model to Think Like a Lawyer: https://arxiv.org/abs/2212.01326
Good general technical primer “Stanford Webinar - GPT-3 & Beyond”: https://youtu.be/-lnHHWRCDGk
The current version of this episode: https://law.mit.edu/pub/ideaflow15
For more episodes of IdeaFlow, see: https://law.mit.edu/media
To signup for IdeaFlow episodes: https://forms.gle/aZbxfsEHkM7egeyf8
Host: Dazza Greenwood, Executive Director, law.MIT.edu
Guest: Damien Riehl, VP, Litigation Workflow and Analytics Content, Fastcase
Date: Tuesday, February 21st, 2023 at 12:00 PM Pacific / 3:00 PM Eastern
I'm a technology lawyer who has advised clients on tech, litigated tech issues, remediated cybersecurity issues, and developed software. My legal experience is diverse (e.g., counseling, complex business litigation, financial litigation, intellectual property, and appeals), working for a variety of clients (e.g., large businesses, small businesses, nonprofits, and individuals).
I have also designed and developed software, implementing cutting-edge technologies (e.g., artificial intelligence, machine learning, natural language processing) to improve the practice of law. I frequently speak and write on topics that discuss societal and legal changes through technology: Internet law, computer and technology law, copyright, and trademark law, cybersecurity, and data privacy.
In the past, I managed digital forensics and cybersecurity engagements to bolster clients' data security and resilience — both reactively and proactively. I also worked with clients to assist e-discovery and transactional workflows by implementing AI (e.g., NLP, clustering, and data analytics).
I currently lead the design, development, and expansion of products at Fastcase, integrating AI-backed technologies to improve legal workflows and to power legal data analytics.
My legal and technology work improves businesses and legal practice, benefiting my clients, lawyers, and the judiciary.