Garrett O'Brien Indoors/outdoors.

Archive

A collection of 8 issues

Featured

Document chat for the masses: building with Fixie AI

Every other large language model-related Twitter thread seems to be some version of the following: “Introducing PiperAI, a new way to chat with your {arbitrary data}, built using {foundation model API}, LangChain, and {vector store}” Document chat is an obvious and powerful use case for LLMs because it offers knowledge

Latest

Failure on the Emmons Glacier

Back in May, Helen and I made a decently ambitious attempt to climb and ski the Emmons Glacier on Mt. Rainier. The Emmons is the largest glacier in the contiguous US, covering nearly four square miles of Mt. Rainier's northeastern flank. We'd recruited a third skier

Chamber of reflection

I recently closed a 5-year chapter of my career, a majority of my working life. I'm always surprised by how these things happen. A bit of anticipation and minimal fanfare, then one day it's just over and you're sitting at home reflexively opening a

Exposure on Mt. Shuksan

Mt. Shuksan sits on a glacial throne at the head of the White Salmon Creek valley, towering nearly 6000 feet over the valley floor. Shuksan is the most photographed mountain in the North Cascades, but I can't imagine the hordes of tourists snapping phone pics from Artist Point

Chair Peak Circumnav

An hour east of Seattle, Chair Peak towers over the Alpental Valley of Snoqualmie Pass. The mountain guards the Alpine Lakes Wilderness and offers steep, complex terrain for skiers and mountaineers. Last weekend, Helen and I set off to attempt the Chair Peak Circumnavigation, a classic, logistically engaging route that

2023 on Skis (Mostly)

I set a few skiing goals in 2023, most of which got promptly thrown into the meat grinder of circumstance. Despite the challenges, skis took me to a few incredible places in 2023. Here are a few that stand out: January High into the Alpental valley and away from heartache

Document chat for the masses: building with Fixie AI

Every other large language model-related Twitter thread seems to be some version of the following: “Introducing PiperAI, a new way to chat with your {arbitrary data}, built using {foundation model API}, LangChain, and {vector store}” Document chat is an obvious and powerful use case for LLMs because it offers knowledge

Silver Peak Scramble

Building company blog posts with GPT-3

Webmasters host it, and sales teams send it, but can an AI write it? How long would it take, using GPT-3, to create a thought leadership piece that hits the sweet spot of mediocre and publishable? I thought I’d find out.