cody collier
@cmcollier
a builder ⌁ always learning :: ml・search・code・data
Added a new entry in my logbook. I looked into the terminology around LLM tool use and function calling. codycollier.com/lx/2025/termin…
If you're a dev and you can explain how you write and assemble code in clear, effective English then don't worry. YGMI.
This is a nicely written reference, from Elastic, for embedding memory sizing. Concise and clear in the details. elastic.co/docs/deploy-ma… I should build a little web app for sizing based on data schema, engine (Elastic, Vespa), and node resources.
If you're into search operations and architecture, we're entering into one of the most interesting periods in a long time. And it's not because of embeddings, vector DBs, hybrid search, or RAG based chat. It's because retrieval has a whole new customer base in the form of…
There is so much arbitrage opportunity sprinkled throughout daily life right now, just with knowing how to use the consumer AI services much less the APIs and more complex machine learning.
real.
I got fired today. I'm not sure why, I personally don't think there is a reason, or that it's important. When I joined twitter, I joined because of the engineers I met in SF. They seemed happy. They were having fun. Engineers at play. Engineers that were enabled. It was good!
It's cool how @cursor_ai seems to be adding a sequence of my viewed code into a context buffer. I was looking at several relevant code chunks, and that seemingly informed the tab completion when I placed the cursor where I wanted to create new functions in another file.
tab completion in @cursor_ai is starting to feel like it should be called thought completion
It's generally true I can generate and iterate to useful code more quickly with AI. However, a more interesting part of the experience is that it's a different level of energy required. Also, if I'm generating code to help with analyzing some data, I don't feel like I'm…
What AI is doing is separating people who prioritize outcomes from people who prioritize internal craft.
. @ProgramWithAi shared a talk about how MCPs are boring and it can be more powerful to just provide the LLM with a tool like eval(). It reminded me once again, how much we need to relinquish certain kinds of historic controls. These tools need different guards.
How Anthropic defines agents and how PocketFlow abstracts them codycollier.com/lx/2025/anthro…
The cost and time to produce code is trending to zero. This isn't just a disruption to the cost of doing business. It's also opening up new green fields for implementation patterns and options. Just in time code generation is one example. At the same time, we are upending user…
Ok. It's time to learn about the internal mechanisms of agents. codycollier.com/lx/2025/journe…
This post about AI augmented programming is getting lots of attention. It's interesting and has plenty of pointed remarks. The responses though, across communities, read like a Rorschach test. fly.io/blog/youre-all…
