Okay, I’ve gone through a few different iterations with my newsletter, the name has changed a few times, and the frequency has been sporadic at best. Now I feel like I have a little more direction on where I want to go with this, and in many ways, feeling more free now that it doesn’t have a name that narrows the focus, it’s just a newsletter from a guy named Morgan.
One big realization that I had, is that I’m such an insanely curious person, and I’m discovering so many new and interesting things, why not just share those and forget the idea of writing long-format posts? We’re all busy, and I’m subscribed to a bunch of newsletters, that I like, but I find I’m too busy to read the longer posts and end up having AI summarize them for me.
So for my newsletter, I want to instead focus on lots of interesting things, stuff that has caught my eye, and just write a few sentences about it, share a link, and move onto the next. My hope is, every issue will have something interesting in it that will make you think a bit more deeply about a topic or a technology.
Oh and since I have quite a few new subscribers, probably good to do a little re-intro:
Hi, I’m Morgan 👋
I’m the cofounder and CTO of Bold Metrics, we’re an AI company doing some interesting stuff with apparel brands and retailers, helping them unlock the power of body data. I’m not a sales or marketing person so I’ll leave it there, not here to pitch you, but now you know what I do.
A long time ago, in a galaxy far, far away, I went to Carnegie Mellon and studied Computer Engineering and Computer Science. While I was in school, I got really interested in optimization techniques, specifically processor-level optimization using things like C and Assembly. This was my favorite book, I still have it on my desk, probably always will.
Fast-forward a bit and I fell in love with Python, and today, most of the coding I do is in Python, but I’ve been getting into Rust a bit this year and that’s been pretty darn interesting. That being said, these days I’ll be the first to admit, I’m a mediocre coder at best. My focus, as a founder and CTO is on my team. I lead a truly amazing engineering and data science team, with some of the most brilliant and incredible people on the planet. It is humbling to be able to work with such an amazing team - building and leading teams is my greatest joy in life.
Most of the topics I’ll cover here are going to be about things like optimizing and building interesting AI agents and small LLMs, agentic coding, interesting libraries or optimizations that people can leverage, and probably some robotics stuff here and there because I love robots.
Right now I have no sponsors and no subscription fee. That could change, I guess I am open to both, but haven’t thought too much about it yet, so this is where we are today.
Okay, enough from me - here’s some fun stuff that’s on my radar, and now is on yours.
Autoresearch
If you don’t know what Autoresearch is, stop everything, go to this Github repo, or read one of the zillion things Karpathy has written about it on X (here’s a good one). I honestly think Autoresearch could be the single most important technological advance introduced this year.
—
AI trading agent based on Autoresearch
If you think Autoresearch is interesting, and want to check out one of the applications of it that I feel like could be going in a very fascinating directions, check out ATLAS, it’s a self-improving AI trading agent.
—
GStack
Garry, the CEO of Y Combinator has been coding like crazy with Claude. Through the process he’s developed a pretty badass Claude Code setup, 10 opinionated tools that serve as CEO, Eng Manager, Release Manager, Doc Engineer, and QA. I’ve been using it, and it’s definitely way better than any optimizations I’ve ever tried myself, worth trying, I can’t unsee what I’ve seen now.
—
Inference.sh
Discovered this last week, haven’t had a chance to play around with it yet, but it looks too cool not to share. Essentially inference.sh is an AI workspace where agents can actually do things. It solves the problem that a lot of people have with AI assistant’s, they can answer questions, but doing things, not so much. I think they explain it better than me so here’s two sentences that I think make it standout as something pretty neat:
“gives AI agents the ability to use tools. Real tools. Apps that generate images, transcribe audio, process data, and more.
You describe what you want. The agent figures out which tools to use, runs them, and gives you the result.”
—
The MCP + CLI Section
There has been so much discussion lately on MCPs vs. CLIs, which is better, when to use each, etc. I shared a tweet last week that went crazy viral, it’s the most viewed tweet I’ve ever written, so I think it’s safe to say, this is a hot topic.
In case you missed it, here’s the tweet:
So, I thought this was such an insanely hop topic right now, I made a little section this week just dedicated to it. I found a lot of interesting articles, but thought I’d share four that really stood out to me that I think other people might find interesting too:
MCPs, CLIs, and skills: when to use what
https://jngiam.bearblog.dev/mcps-clis-and-skills-when-to-use-what/
MCP vs. CLI for AI-native development
https://circleci.com/blog/mcp-vs-cli/
CLI Hub - turn any MCP Server into a CLI
https://github.com/thellimist/clihub
—
Obsidian + Claude Code
This combo is so good, I can’t even do it justice. Greg does a stellar job breaking it down, it’s worth spending the entire hour watching this because it will save you soooo much time in your life if you connect these two.
—
The agent observability gap
Super interesting read about agent observability, which I think is a topic many of us should be thinking more deeply about, because it’s only becoming more important by the week.
—
Understanding Function Calling: The Bridge to Agentic AI
I still see a lot of confusion around how AI Agents call functions, and I was going to whip up a little article myself, then found this, and it’s what I’ve been sending around, so thought, heck - include it.
—
4G LTE Antenna (to read your electricity meter)
This one is just too fun not to share. You can monitor your electricity meter using a 4G antenna, and here’s a really inexpensive one that should do the trick. And no, you don’t need to read an article about how to do this, just copy and paste this link into ChatGPT or Claude, and ask it how to do it.
Okay, that’s all I got, thanks for reading and I hope you like the new format! Right now I have no subscription to sell you, and no sponsors, so I guess there’s nothing more to say.
See you next week, and yup - I’m going for weekly.
Morgan
