AI & Life

Think -> Experiment -> Create -> Serve

RLHF from Shakespeare

I tried to finetune LLM with RLHF to generate positive tone message from Shakespeare Corpus. Here is what I learnt.

3 min read · August 16, 2023

2023 · Project · AI
ARENA learning experience

I summarized my learning experience about ARENA.

3 min read · August 1, 2023

2023 · Project Reflection · AI
How to get gold medal in Kaggle competition, from a Competition Master perspective.

I summarized 7 key points about how to get a Kaggle competition gold medal.

2 min read · July 29, 2023

2023 · Reflection · AI
Implementing PPO from scratch

I tried to implementing PPO from scratch and apply it to Procgen environment. Here is what I learnt.

3 min read · July 23, 2023

2023 · Project · AI
Replicating Scaling Laws by using MNIST data

I tried to replicating scaling laws result by using MNIST data. Here is what I learnt.

2 min read · July 10, 2023

2023 · Project · AI