Phillip Carter
Hi! I occaisionally write stuff and put it on this site.
In my day job, I work at GitHub on the cloud platform for running agents. This allows me to achieve a special kind of AI psychosis known as "why does the system keep falling over due to wild and wacky reasons?".
I used to work on a few other things:
- Automations platform at Salesforce
- AI and OpenTelemetry at Honeycomb and the OTel community
- F# language, VS tools, and other suff at Microsoft
Outside of work I'm doing stuff with family or friends, preferably in the mountains somehow.
Posts
The bluster of agent swarms writing code
Agent swarm systems produce a lot of code but not much more working software.
Don't build your own CRM
You really don't want to be in the business of building your own Salesforce.
I don't know how to evaluate coding models
The rate of LLM improvements for coding keeps increasing, and I can't keep up.
My favorite F# code I've written
The one time I was actually pretty dang clever with this coding thing
What if AI isn't a Bubble?
I'm not sure people are prepared for a world where AI ends up not being a bubble.
AI Observability is Just Application Observability
AI Observability is just application observability with a few added concerns.
Lame Duck Teams
At big software companies, you end up with a lot of teams who exist far longer than they need to.
The exhaustion of keeping up with AI models
AI models keep improving, but in uneven ways and with benchmarks that don't mean much. It can be tiring.
A few ways to support a pregnant partner
Some things I learned about being helpful to a pregnant partner
Some cool things about lifting weights
My observations on lifting heavy rocks after a few years
Using LLMs as a search engine
A quick perspective on using LLMs as search engines
LLMs Are Weird Computers
A perspective on AI models as an inverted computing paradigm
How I code with LLMs these days
Practical tips for developers looking to use AI coding assistants
LLM training is finally getting more efficient
DeepSeek V3 shows a 14x reduction in compute to train a state-of-the-art AI model.
A case for academic debate in product development
A small screed about something that's bothered me about modern Product Management practices.
The Observability CAP Theorem
My elaboration on why I think Observability as a CAP theorm of its own.
Three properties of data for making LLMs awesome
How Data Relevancy, Data Magnitude, and Data Quality impact the effectiveness of LLMs for your use cases.
When the readability of Go falls off a cliff
My take on how "Go is readable" doesn't mean much to me.
The best docs are the docs you don't need
My opinion on the intersection of docs, developer tool ergonomics, and building things deliberately.
Goodbye Microsoft, Hello Honeycomb
My departure message to the F# community