Community

WE HAVE APOSTROPHES Y'ALL

Some updates for Subcurrent, an open source service that creates a stream of content from the Astoria tech community.

AI

If you didn't have a question, don't subject yourself to an endless stream of answers

With LLMs, looking for the big picture or seeking the pros, cons, and white space in and around my path of inquiry is really all on me as the human.

AI

No cloud required: local LLMs as a practical app dependency

TL;DR: Ollama on a MacBook Air with M4 is great and it's a taste of the future. Developers should try it now.

Product Management

Gall's law

"A complex system that works is invariably found to have evolved from a simple system that worked."

RSS

Subcurrent RSS bot for Discord

Subcurrent now posts RSS updates to Discord. Will it spark discussion around the content?

Social Media

Facebook → /dev/null

Wherein 9 years after I decide to do so, I delete my Facebook account.

Community

Subcurrent

Subcurrent brings together content from Astoria Tech community members into a single web page and RSS feed.

AI

Zero to Deploy with Claude.ai and Val Town

Today I streamed my first video on Twitch, showing how to use Anthropic's Claude.ai and Val Town to ship a small frontend web app.

AI

Batch loading resources in EmbedJS for RAG

A look at dynamically batch loading RAG resources with EmbedJS.

AI

AI-powered fun in p5.js

Using AI in p5.js by wiring up a sketch to a serverless proxy function on Val Town.

Node.js

You're going to Val Town

Val Town's runnable vals (their word for "gists") can be triggered manually, via email, or as an HTTP endpoint or cron job.

AI

RAG in Node.js with EmbedJS

A look at a Node.js library called EmbedJS for RAG AI applications along with a repo to help you get started.