AI RLHF Training
TextEvaluation Rating
Worked with Truing as part of a project to build AI browser based agents. My role was to evaluate the agent's computer use to understand the efficacy of its action relative to the user request. I evaluated AI responses based on key metrics - accuracy, completion and AI performance.
Worked with Truing as part of a project to build AI browser based agents. My role was to evaluate the agent's computer use to understand the efficacy of its action relative to the user request. I evaluated AI responses based on key metrics - accuracy, completion and AI performance.
2022 - Present