Controlled and compliant AI applications (Practical AI #225)
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. In this episode, Chris interviews Daniel about his new company called Prediction Guard, which addresses these issues. They discuss 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" models.
Embed this episode
Chapters
- 0:00 Welcome to Practical AI
- 1:02 Growing AI interests
- 2:36 Disclaimer?
- 4:17 Co-host & guest?
- 5:34 Pressures of AI
- 11:47 Unlocking more value
- 14:50 Sponsor: Changelog News
- 16:43 Open access models
- 20:25 Where do we place our bets?
- 25:35 Structured 7 typed output
- 30:33 Problems of the space
- 37:55 Determining your needs
- 41:22 Ease of use
- 43:03 No code world
- 45:27 The future question
- 48:06 Goodbyes
- 48:52 Outro
No transcript yet.