Posts

Andrew Fairless, Ph.D.

blue-green banner

2024-10-22

What I Read: standard error
2024-10-21

What I Read: LLM evaluation
2024-10-17

What I Read: Data Flywheels, LLM
2024-10-16

What I Read: Use-cases, inverted PCA
2024-10-15

What I Read: Improving Language Models, Practical Size
2024-10-10

What I Read: Hidden Infinity, Preference Learning
2024-10-09

What I Read: Illustrated AlphaFold
2024-10-07

What I Read: Extrinsic Hallucinations, LLMs
2024-10-03

What I Read: decision analysis, significance testing
2024-10-01

What I Read: What can LLMs never do?
2024-09-30

What I Read: Sliding Window Attention
2024-09-25

What I Read: bare metal to 70B
2024-09-24

What I Read: What’s Fair, What’s Hard
2024-09-23

What I Read: Detecting hallucinations, LLMs, semantic entropy
2024-09-19

What I Read: Structured Generation, LLMs
2024-09-18

What I Read: AI Engineers, Search
2024-09-16

What I Read: Musings on AI Engineering
2024-09-12

What I Read: SSD, Database
2024-09-10

What I Read: Command-line Tools, Faster
2024-09-09

What I Read: Scaling to Multi-Terabyte Datasets
2024-09-05

What I Read: notebooks, McDonalds of code
2024-09-04

What I Read: LLMs train LLMs
2024-09-03

What I Read: Summarization, LLMs
2024-08-29

What I Read: Logarithms, Heteroskedasticity
2024-08-27

What I Read: string ufuncs, NumPy 2.0
2024-08-26

What I Read: neural systems understanding
2024-08-22

What I Read: Cookiecutter Data Science V2
2024-08-21

What I Read: KL All You Need
2024-08-19

What I Read: What We Learned Building LLMs
2024-08-15

What I Read: Merge Large Language Models
2024-08-14

What I Read: Transformers by Hand
2024-08-13

What I Read: LLM Pipelines, DSPy
2024-08-07

What I Read: LLM evaluation
2024-08-06

What I Read: LLM, DSPy Assertions and Suggestions
2024-08-05

What I Read: implicit biases, LLM
2024-07-31

What I Read: AI, Light-Based Chips
2024-07-30

What I Read: Labeling, Uncertainty Sampling
2024-07-29

What I Read: Platonic Hypothesis
2024-07-25

What I Read: Game Theory, AI
2024-07-24

What I Read: StandardScaler
2024-07-23

What I Read: PostgreSQL
2024-07-18

What I Read: time series, Gaussian processes
2024-07-17

What I Read: Matryoshka Embedding
2024-07-15

What I Read: LLMs, Open Source
2024-07-10

What I Read: anti-patterns, data reuse
2024-07-09

What I Read: Hallucinations, AI
2024-07-08

What I Read: Ring Attention
2024-07-02

What I Read: Kalman Filter
2024-07-01

What I Read: Data Science, Mostly Dispatch
2024-06-27

What I Read: Dont put notebooks into production