Jeremy HuffThe Tech Stack and Tooling Behind Purple Go’s HIPAA-Compliant, LLM-Based Prescription Document…This article is a walkthrough of our latest solution to a tough challenge in healthcare AI automation that led us to a somewhat…Nov 27, 2023Nov 27, 2023
Jeremy HuffWhat I Learned at Google Cloud Next 2023: LLMs, Data, & Production App PipelinesGoogle’s annual 3-day, cloud-focused Next conference wrapped last week, and it was awesome to geek out and see what Google and other…Sep 6, 20231Sep 6, 20231
Jeremy HuffPaLM 2 Latency MeasurementsI did some profiling on latency of the PaLM 2 API this morning! Here’s what I found. These tests use the text-bison@001 model in the…Aug 24, 2023Aug 24, 2023
Jeremy HuffIntroducing rp, a Lightweight Framework for Building Efficient Execution Chains in Gorp, the “request pipeline” framework, makes server endpoints with multiple execution steps easier to build, maintain, and optimize. It is…Aug 14, 2023Aug 14, 2023
Jeremy HuffA Short Survey of LLM Tech Stack Options and ConsiderationsSay you’re a developer in July 2023 that’s aiming to take advantage of LLMs’ capability to do in-context learning, and you want to build an…Jul 28, 2023Jul 28, 2023
Jeremy HuffWhy I Started Building Apps with LLMsSoftware’s shift towards AI in the eight months since ChatGPT’s release has been one of the biggest transitions I’ve seen in my career. It…Jul 20, 20231Jul 20, 20231
Jeremy HuffHere Begins My Writing for 2023. I Hope You Will Find It Enjoyable.We will see how this unfolds in the weeks and months ahead, but I have decided to write a series of short articles on some topics I…Jul 11, 20231Jul 11, 20231