Daily Reading List – January 10, 2024 (#236)

This is supposed to be a “light meeting” week at work. In unrelated news, I had twelve meetings today. Fortunately, there wasn’t a dud in a bunch and I could still make time to read some interesting items today.

[article] When Your Boss Gives You a Totally Unrealistic Goal. Hey, I did this to my team yesterday! But on purpose. Outlandish goals force unconstrained thinking. We do the best we can, and no one (on my team) will get dinged because we didn’t reach it. Aim high.

[article] What Temperature Means in Natural Language Processing and AI. Have you noticed this property in LLM APIs or UIs? This article explains what temperature is about.

[docs] Perform automatic side-by-side evaluation. Wow, evaluate the performance of two LLMs, side by side to see which gives better responses? This is now part of Vertex AI.

[blog] Introducing the Dataflow ML Starter project: A practical template to develop and deploy Dataflow ML jobs. While I don’t use “starter projects” as my actual baseline, I do often use these sorts of things as a way to learn, and then copy aspects I want to reuse.

[article] The return of the majestic monolith. Long post, but good points about doing what’s right for your use case, not just what’s trendy.

[blog] 2024 Predictions from the Condensing the Cloud Team. The Battery Ventures team has a pulse on what the market is buying, so I’ll listen to predictions from these VCs. Many of these feel spot on.

[blog] Getting started with AI notebooks and Jupyterhub on GKE. Is your team doing more with Jupyter notebooks? If so, you likely have some platform for folks to interact with them. Here’s a way to run such an experience on Kubernetes.

[blog] 10 microservices design patterns for better architecture. The Capital One team has another good post that looks at some common design patterns for those doing microservices.

[blog] Gemini, the stylist… Would you trust an LLM to offer to hairstyle suggestions? Um, maybe? Abi built a fun app that used Gemini and Imagen2 to create suggestions that she accepted.

##

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: