Adiel Edwards

Key Skills

Software

Scale AI

Other

Top Subject Matter

No subject matter listed

Top Data Types

Image

Text

Top Task Types

Evaluation Rating

Prompt Response Writing SFT

RLHF

Text Generation

Text Summarization

Freelancer Overview

I am a Bilingual Freelance Writer & Artificial Intelligence (LLM) Trainer who is fluent in both English and Spanish with previous experience on Outlier.ai with a feedback rating off 4.7 out of 5 stars for a Bilingual AI Training project that focused on honing and rigorously evaluating and isolating key elements in a language model answer that led to quantifiable and valuable data for clients. Once I understand the nuances of an AI project, I enjoy specializing in that project and take pride in my work and fixing/preventing any errors I learn about in feedback. I was promoted to the job position of Reviewer on that project, in charge of reviewing the attempts of other trainers. I worked using Outlier.ai's (Scale AI) internal on-site tools to perform AI Training and evaluate and train the AI models and grade them for efficacy using Reinforcement Learning from Human Feedback. I also excel at projects that involve classification, summarization, fine-tuning, evaluation, and creating prompts that force language models to produce high-quality results.

Labeling Experience

Cypher Evals C

Scale AITextText GenerationTranslation Localization

In this project you will rate two model generated responses separately across various dimensions. Provide preference ranking scores. Write a justification for the response preference ranking and explain the specifics and logic behind your decision.

In this project you will rate two model generated responses separately across various dimensions. Provide preference ranking scores. Write a justification for the response preference ranking and explain the specifics and logic behind your decision.

2024

Crackers 2 Evolution

Scale AITextText GenerationRLHF

In Crackers Evolution, you will have a natural conversation with a model and evaluate the quality of the model responses it generates. You will produce deviations in the model responses.

In Crackers Evolution, you will have a natural conversation with a model and evaluate the quality of the model responses it generates. You will produce deviations in the model responses.

2024 - 2024

White Wolf Rlhf

Scale AITextText GenerationRLHF

Power up the future of AI by training a next-gen LLM with RLHF.

Power up the future of AI by training a next-gen LLM with RLHF.

2024 - 2024

Aurora Smile

Scale AITextText GenerationRLHF

Give feedback on a brand new AI model! Write prompts that make a model response fail, and then give feedback and help improve the model.

Give feedback on a brand new AI model! Write prompts that make a model response fail, and then give feedback and help improve the model.

2024 - 2024

Starfish Mint v2

Scale AITextText GenerationRLHF

In this project, you will write a prompt that causes model failure and then improve the response!

In this project, you will write a prompt that causes model failure and then improve the response!

2024 - 2024

Show more

Education

Work History