May 2023 – Andrew Fairless, Ph.D.

What I Read: smaller LLMs, more tokens

By Andrew Fairless on May 31, 2023May 1, 2023

https://www.harmdevries.com/post/model-size-vs-compute-overhead/ Go smol or go homeWhy we should train smaller LLMs on more tokensHarm de VriesApr 13, 2023 “However, for most use cases you should not train a compute-optimal LLMContinue readingWhat I Read: smaller LLMs, more tokens

What I Read: Few Shot, Recommenders, LLMs

By Andrew Fairless on May 30, 2023May 1, 2023

https://blog.reachsumit.com/posts/2023/04/llm-for-recsys/ Zero and Few Shot Recommender Systems based on Large Language ModelsSumit Kumar2023-04-10 “Many researchers have recently proposed different approaches to building recommender systems using LLMs. These methods convert differentContinue readingWhat I Read: Few Shot, Recommenders, LLMs

What I Read: LLM applications, production

By Andrew Fairless on May 29, 2023May 1, 2023

https://huyenchip.com//2023/04/11/llm-engineering.html Building LLM applications for productionChip HuyenApr 11, 2023 “It’s easy to make something cool with LLMs, but very hard to make something production-ready with them.”

What I Read: Prompt Engineering

By Andrew Fairless on May 25, 2023May 1, 2023

https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/ Prompt EngineeringLilian WengMarch 15, 2023 “Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes withoutContinue readingWhat I Read: Prompt Engineering

What I Read: Multimodal Models

By Andrew Fairless on May 24, 2023May 1, 2023

https://www.kdnuggets.com/2023/03/multimodal-models-explained.html Multimodal Models ExplainedBy Nate RosidiMarch 27, 2023 “…multimodal learning is an exciting new field of AI that seeks to replicate this ability by combining information from multiple models. ByContinue readingWhat I Read: Multimodal Models

What I Read: human touch, LLMs

By Andrew Fairless on May 23, 2023May 1, 2023

https://mewelch.substack.com/p/putting-the-human-touch-on-llms Putting the human touch on LLMsMolly WelchMar 30 “Techniques like RLHF help align large language models with people’s values and preferences. Is that a good thing?”

What I Read: MLOps, Data Engineering

By Andrew Fairless on May 18, 2023May 1, 2023

https://www.cpard.xyz/posts/mlops_is_mostly_data_engineering/ MLOps is Mostly Data Engineering.22 March 2023Kostas Pardalis “The question here is… why do we need a whole new category of products?… The true need here is developer toolingContinue readingWhat I Read: MLOps, Data Engineering

What I Read: Graph Neural Networks

By Andrew Fairless on May 17, 2023March 30, 2023

https://www.assemblyai.com/blog/ai-trends-graph-neural-networks/ AI trends in 2023: Graph Neural NetworksMarco RamponiDeveloper Educator at AssemblyAIMar 21, 2023 “In the last couple of years Graph Neural Networks have quietly become the dark horse behindContinue readingWhat I Read: Graph Neural Networks

What I Read: Topic Modeling

By Andrew Fairless on May 15, 2023March 30, 2023

https://maria-antoniak.github.io/2022/07/27/topic-modeling-for-the-people.html Topic Modeling for the PeopleMaria Antoniak “…I’m going to share a set of steps that you can follow to get coherent topics from most datasets. You can think ofContinue readingWhat I Read: Topic Modeling

What I Read: GPT, Ranking

By Andrew Fairless on May 11, 2023March 30, 2023

https://messyprogress.substack.com/p/gpt-is-rather-good-at-feed-ranking GPT is Rather Good at Feed RankingRob EnnalsMar 7 “If ranking is as easy as saying what should rank highly, then lots of interesting things happen.”

Month: May 2023