Controlled and Compliant AI Applications // Daniel Whitenack // LLMs in Production Conference Part 2

// Abstract
You can’t build robust systems with inconsistent, unstructured text output from LLMs. Moreover, LLM integrations scare corporate lawyers, finance departments, and security professionals due to hallucinations, cost, lack of compliance (e.g., HIPAA), leaked IP/PII, and “injection” vulnerabilities. This talk will cover some practical methodologies for getting consistent, structured output from compliant AI systems. These systems, driven by open access models and various kinds of LLM wrappers, can help you delight customers AND navigate the increasing restrictions on "GPT" …

abstract ai applications applications build compliance conference corporate cost daniel finance hallucinations hipaa lawyers leaked llm llms part pii practical production professionals security systems talk text unstructured vulnerabilities