Ex-CTO building independently. Honest documentation of what works, what doesn't, and what I'm learning — AI tools, directory sites, self-hosted infrastructure
There's a flag in Claude Code called --dangerously-skip-permissions . It does what it sounds like. The agent runs as you, with your SSH keys, cloud credentials, Keychain, every project on your machine. Full autonomy. No approval prompts. This is where the actual productivity lives. I never turned it on.
With many recently released models (such as Claude 3.7), everybody and their mother is happy with how it writes code. Still, it is an intermediary step to more significant goals in disrupting software development. We're still doing baby steps. And, possibly, in the wrong direction.
Programming has always been about managing complexity—finding ways to express our intentions to computers while maintaining human readability and understanding. Today, we face a new paradigm: generating code using large language models (LLMs). But is this solving the software development challenge, or are we adding another layer of
As I wrote in my post on the state of AI-based software development , AI still has many limitations when applied to software development. However, I found one case in which it improved my productivity tenfold without any meaningful downsides. It's learning a new code base. It's
In the last few months, I've been trying to program using large language models. I want to collect my impressions in a series of notes about which ideas seemed successful and which seemed inconvenient and possibly even lead to a dead-end.