https://www.fast.ai/posts/2023-09-04-learning-jumps/ Can LLMs learn from a single example?Jeremy Howard and Jonathan WhitakerSeptember 4, 2023 “We’ve noticed an unusual training pattern in fine-tuning LLMs. At first we thought it’s a bug,
What I Read: To Understand Transformers, Focus on Attention
https://drscotthawley.github.io/blog/posts/Transformers1-Attention.html To Understand Transformers, Focus on AttentionScott H. HawleyAugust 21, 2023 “To Understand Transformers, Focus on Attention”
What I Read: A.I. Tool Diagnoses Brain Tumors
https://www.nytimes.com/2023/10/11/health/ai-tumor-diagnosis-brain-cancer.html New A.I. Tool Diagnoses Brain Tumors on the Operating TableBenjamin MuellerOct. 11, 2023, 11:00 a.m. ET “New A.I. Tool Diagnoses Brain Tumors on the Operating Table”
What I Read: AI, Images
https://www.quantamagazine.org/the-ai-tools-making-images-look-better-20230823/ The AI Tools Making Images Look BetterAmos ZeebergAugust 23, 2023 “Researchers have discovered ways around a fundamental trade-off between accuracy and beauty in digital images.”
What I Read: LLM-based Products
https://eugeneyan.com/writing/llm-patterns/ Patterns for Building LLM-based Systems & Productseugeneyan “This post is about practical patterns for integrating large language models (LLMs) into systems and products.”