Andrew Fairless – Page 26 – Andrew Fairless, Ph.D.

What I Read: Kubernetes, Batch

By Andrew Fairless on July 25, 2023June 15, 2023

https://betterprogramming.pub/kubernetes-was-never-designed-for-batch-jobs-f59be376a338 Kubernetes Was Never Designed for Batch JobsAnd what it would look like if it had beenMeadowrunSep 1, 2022 “…Kubernetes is philosophically biased towards microservices over batch jobs. This resultsContinue readingWhat I Read: Kubernetes, Batch

What I Read: data drift

By Andrew Fairless on July 20, 2023June 15, 2023

https://www.nannyml.com/blog/when-data-drift-does-not-affect-performance-machine-learning-models Don’t let yourself be fooled by data driftby Santiago VíquezMay 31, 2023 “While data drift detection is indeed a key component of a healthy monitoring workflow…. not all dataContinue readingWhat I Read: data drift

What I Read: Hard Stuff, Building Products, LLMs

By Andrew Fairless on July 19, 2023June 15, 2023

https://www.honeycomb.io/blog/hard-stuff-nobody-talks-about-llm All the Hard Stuff Nobody Talks About when Building Products with LLMsBy Phillip CarterLast modified on June 1, 2023 “There’s a lot of hype around AI, and in particular,Continue readingWhat I Read: Hard Stuff, Building Products, LLMs

What I Read: Prompt injection

By Andrew Fairless on July 17, 2023June 15, 2023

https://simonwillison.net/2023/May/2/prompt-injection-explained/ Prompt injection explained, with video, slides, and a transcriptSimon Willison “…prompt injection is an attack against applications that have been built on top of AI models…. Where it getsContinue readingWhat I Read: Prompt injection

What I Read: What, Why ChatGPT

By Andrew Fairless on July 12, 2023June 15, 2023

https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/ What Is ChatGPT Doing … and Why Does It Work?February 14, 2023Stephen Wolfram “That ChatGPT can automatically generate something that reads even superficially like human-written text is remarkable, andContinue readingWhat I Read: What, Why ChatGPT

What I Read: In-Context Learning

By Andrew Fairless on July 11, 2023May 31, 2023

https://thegradient.pub/in-context-learning-in-context/ In-Context Learning, In ContextDaniel Bashir29.Apr.2023 “…in-context learning (ICL). In this paradigm, an LLM learns to solve a new task at inference time (without any change to its weights) byContinue readingWhat I Read: In-Context Learning

What I Read: AIs producing own training data

By Andrew Fairless on July 10, 2023May 31, 2023

https://thegradient.pub/software2-a-new-generation-of-ais-that-become-increasingly-general-by-producing-their-own-training-data/ Software²: A new generation of AIs that become increasingly general by producing their own training dataMinqi Jiang22.Apr.2023 “We are at the cusp of transitioning from “learning from data” toContinue readingWhat I Read: AIs producing own training data

What I Read: Scaling Up

By Andrew Fairless on July 6, 2023May 31, 2023

https://motherduck.com/blog/the-simple-joys-of-scaling-up/ The Simple Joys of Scaling UpJordan Tigani2023/05/11 “If you can do the job on a single machine, isn’t that going to be a better alternative?”

What I Read: Natural Language, supply chains

By Andrew Fairless on July 5, 2023May 31, 2023

https://datasciencecampus.ons.gov.uk/using-natural-language-processing-for-the-analysis-of-global-supply-chains/ Using Natural Language Processing for the analysis of global supply chainsIoannis Kaloskampis Bernard Peat Charles McGowan Paige Hunter Melissa Bui David BradnumMay 11, 2023 “…we explored whether cutting-edge dataContinue readingWhat I Read: Natural Language, supply chains

What I Read: Against LLM

By Andrew Fairless on June 29, 2023May 31, 2023

https://explosion.ai/blog/against-llm-maximalism Against LLM maximalismby Matthew HonnibalMay 18, 2023 “However, LLMs are not a direct solution to most of the NLP use-cases companies have been working on… if you want toContinue readingWhat I Read: Against LLM

Author: Andrew Fairless