What Will You Learn
Explore ethical, social, and technical challenges in AI. Aim for alignment with human values and societal norms.
- Develop a benchmark to track and improve AI model and prompt performance over time.
- Use moderation models to evaluate and score harmful AI outputs.
- Train and prompt engineer AI models towards or away from specific values.
- Create a values-evaluation model through self-consistency.
- Understand and discuss tokens, values, ethics, reward misspecification, and scalable oversight.
- Apply techniques to reduce AI hallucination, ensure AI confidentiality, and detect sleeper agents.
Who Is This Course For
Experienced developers, managers, and executives
Meet Liz Howard
Liz is a highly technical expert educator and manager, with over 20 years of experience. they have taught over 20,000 people in person and the repeatable processes they developed have graduated an order of magnituge more. Their in-person students are hired at a rate over 98% at an average starting salary of 106k. They have multiple exits (Hackbright, Hipcamp, Galvanize). They have made impacts on the tech industry so large they can be measured in whole percentage points of the national software engineering population.
Join as a Member
Just This Course
Full Price
- Industry mentors
- Participate in active research projects
- Networking events
- Integrate AI into your workflow from the beginning
Underrepresented in Tech Scholarship
- Industry mentors
- Participate in active research projects
- Networking events
- Integrate AI into your workflow from the beginning
Get In Touch
Want to hire us for your staff training or speaking at your conference?
You can email me at liz@themultiverse.school