software engineering – Page 2 – Andrew Fairless, Ph.D.

What I Read: Data Flywheels, LLM

By Andrew Fairless on October 17, 2024July 20, 2024

https://www.sh-reya.com/blog/ai-engineering-flywheel Data Flywheels for LLM ApplicationsShreya ShankarJul 1, 2024 “This diagram illustrates my (idealized) architecture of an LLM pipeline, from input processing through evaluation and logging. It showcases ideas I’llContinue readingWhat I Read: Data Flywheels, LLM

What I Read: bare metal to 70B

By Andrew Fairless on September 25, 2024July 8, 2024

https://imbue.com/research/70b-infrastructure From bare metal to a 70B model: infrastructure set-up and scriptsThe Imbue TeamJune 25, 2024 “…we trained a 70B parameter model from scratch on our own infrastructure that outperformedContinue readingWhat I Read: bare metal to 70B

What I Read: Structured Generation, LLMs

By Andrew Fairless on September 19, 2024July 8, 2024

https://blog.dottxt.co/coding-for-structured-generation.html Coding For Structured Generation with LLMsWill Kurt2024-06-21 “In this post we’re going to go through an example that shows not only how to use structured generation in your LLMContinue readingWhat I Read: Structured Generation, LLMs

What I Read: AI Engineers, Search

By Andrew Fairless on September 18, 2024June 29, 2024

https://softwaredoug.com/blog/2024/06/25/what-ai-engineers-need-to-know-search What AI Engineers Should Know about SearchDoug TurnbullJune 25th, 2024 “Things AI Engineers Should Know about Search”

What I Read: Musings on AI Engineering

By Andrew Fairless on September 16, 2024June 29, 2024

https://www.sh-reya.com/blog/ai-engineering-short Short Musings on AI Engineering and “Failed AI Projects”Shreya ShankarJun 24, 2024 “When we studied the traditional MLOps lifecycle, we found one common pattern across all successful ML products—theirContinue readingWhat I Read: Musings on AI Engineering

What I Read: notebooks, McDonalds of code

By Andrew Fairless on September 5, 2024June 29, 2024

https://yobibyte.github.io/notebooks.html notebooks are McDonalds of codeVitaly Kurin “I later saw the extensive use of notebooks everywhere, even in production, and I don’t laugh anymore. I’m scared and sad.”

What I Read: string ufuncs, NumPy 2.0

By Andrew Fairless on August 27, 2024June 15, 2024

https://labs.quansight.org/blog/numpy-string-ufuncs Writing fast string ufuncs for NumPy 2.0Lysandros NikolaouPublished May 21, 2024 “After a huge amount of work from many people, NumPy 2.0.0 will soon be released, the first NumPyContinue readingWhat I Read: string ufuncs, NumPy 2.0

What I Read: Cookiecutter Data Science V2

By Andrew Fairless on August 22, 2024June 4, 2024

https://drivendata.co/blog/ccds-v2 Cookiecutter Data Science V2by Peter Bull, Jay Qi, Chris KucharczykWed 22 May 2024 “…in the past 5 years, a lot has changed in data science tooling and MLOps. CookiecutterContinue readingWhat I Read: Cookiecutter Data Science V2

What I Read: LLM, DSPy Assertions and Suggestions

By Andrew Fairless on August 6, 2024May 25, 2024

https://learnbybuilding.ai/tutorials/guiding-llm-output-with-dspy-assertions-and-suggestions Guiding LLM Output with DSPy Assertions and SuggestionsBill Chambers “Assertions in DSPy allow you to define strict rules and constraints that the LLM’s output must (or maybe that youContinue readingWhat I Read: LLM, DSPy Assertions and Suggestions

What I Read: LLMs, Open Source

By Andrew Fairless on July 15, 2024May 6, 2024

https://www.aidancooper.co.uk/how-to-beat-proprietary-llms How to Beat Proprietary LLMs With Smaller Open Source ModelsAidan CooperApr 26, 2024 “…we explore the unique advantages of open source LLMs, and how you can leverage them toContinue readingWhat I Read: LLMs, Open Source

Tag: software engineering