Outlier
TextRLHF
I worked on several projects on Outlier, including Aether, Spidey MM and Space Cows. These projects involved working with a LLM, training it in a range of labelling types, including RLHF, prompt response creation and domain specific annotation across a range of subject matters, text evaluation, and monitoring for hallucinations.
I worked on several projects on Outlier, including Aether, Spidey MM and Space Cows. These projects involved working with a LLM, training it in a range of labelling types, including RLHF, prompt response creation and domain specific annotation across a range of subject matters, text evaluation, and monitoring for hallucinations.
2025 - 2026