I will point out that my thread in that list was specifically not about using agents to write code, which I considered then (and still consider now) to be rather absurd. I expected agents to catch on with low-risk activities like search rather than stuff like programming where correctness is actually important.

To my surprise, writing code (poorly) seems to have caught on as the “killer app” for agents, and that’s about where I lost interest and went back to writing databases.

I should say that, while I’m quite sure LLMs are helpful for asking questions, I strongly doubt asking models to write code for you is a good path to learning a language. Similarly, I don’t think you can learn math by asking the model to do problems for you. The part where you have to think about your decisions is the learning part. So just be careful.

Not to be a gatekeeper but “vibe engineering” strikes me as an oxymoron. Vibe is associated with loose and intuitional. Engineering is precise and provable. I can’t tell anyone else what to do or think but I do find the term “vibe engineering” a bit troubling.

What you are describing is simply “agentic coding/programming/engineering” where one hopes you actually review the code very VERY thoroughly.

The “vibe” in “vibe coding” means: “Hey, uh, bro… I mean, computer… can you, like, you know, make me a totally rad todo list? Cool man… (bong sounds).” Sticking “vibe” in front of the term “engineering”—and quite frankly I think “engineer” is a pretty ridiculous term to use for programmers but it sure does help us add some zeros to our pay-cheques so whatever!—is more like: “Excuse me my good sir, I am definitely totally sober and would like you to make a very exquisite todo list that is very secure, I humbly thank you (bong sounds).”

Despite the use of em-dashes, no LLMs were consulted in writing this comment. I’m an OG em dash user and I’m tired of not using them.

I am experimenting with AI Intent Driven Development:

I do use the LSP and TIdewave as an MCP server, but not the paid version, because until I get employed I can only afford what is free, which also limits my ability to develop with AI, once I am using Gemini CLI, which isn’t at the level of Claude Sonnet 4.5, that I briefly played with in a trial.

Some of these threads might also be of interest SS…