I had a tough week, a week ago. My manager pointed out some of the negative side effects of my aggressive adoption of agentic coding, prompting me to rethink how I’m approaching my work.
Continue reading “Agentic coding growing pains”Tag: LLM
The AI Landslide Is Happening
When it comes to AI changing the tech world, we’re at a juncture where you’ve either:
- seen some shit with your own eyes or you believe your imagination of where this is going
- or, you haven’t and you’re dubious
It feels like people are living in a fractured reality. For the moment, that is stable. But reality is not completely subjective. The way we each get to live in the world is shaped by things outside of our subjective perspective. That is going to hit all of us, regardless of what we believe.
Continue reading “The AI Landslide Is Happening”CDAP: a revolutionary way of working with AI agents
I have adopted a new way of taking on complex projects, and it is radically increasing my productivity. The idea is simple: I use documents as the shared canvas for collaboration between myself and chatbot sessions. The result is far more powerful than the sum of its parts.
I call it chatbot+document-assisted projects, or CDAPs.
Continue reading “CDAP: a revolutionary way of working with AI agents”Brave new world: rethinking software development
We’re in the midst of a massive pivot in the entire line of work of software development. At least in some places, like where I work, everything is different.
Continue reading “Brave new world: rethinking software development”Truly persistent terminals in VSCode and Cursor
There are times when I am embarrassed to realize that I have accepted a painful limitation for years. In this case, it is my resistance to restarting my IDEs because I don’t want to lose my terminals. Now, thanks to a burst of motivation and a modern chatbot, I’m setup for my IDEs to resume exactly where they left off.
Continue reading “Truly persistent terminals in VSCode and Cursor”LLMs think
It’s interesting to see scientific people categorically reject the notion that LLMs “think”. People write them off as “fancy autocomplete” or regurgitating their source material, and conclude that they do something categorically different than what humans can do. That it’s all just a parlor trick. I think1 that’s wrong.
Continue reading “LLMs think”
Never Down, Always Up 