In my experiments with SpecKit I was always left wondering "when does it merge all this specs into a single ground truth". I never got there and it felt like a huge missing step.
Now I'm left trying to define/design what a "spec" for communication between humans and coding agents would look like, to power what Birgitta called spec anchored.
> Now I'm left trying to define/design what a "spec" for communication between humans and coding agents would look like, to power what Birgitta called spec anchored.
I feel that now with AI this is something that we have to finally do. Define how we write out a spec and record an architecture semi-formally, and in a way that is human-readable and human-manageable. And in a way that can 1) be consumed partially by an LLM context, rather than entirely (because it may be too big), and 2) have that partial ingestion be enough for it to do real work, either on the spec itself on or on the code, without deviating from the core intentions and architecture.
We tried and failed with the UML and Rational Rose type stuff, I think because it didn't record intentions well enough, was mostly pictures and not words, and seemed to be something that you would create after you finishd a project rather than fill in the details and guide you while you were building it. Hence, the whole idea fell away because it wasn't useful for anything but documentation, maintenance or refactoring; you were already selling the product before the spec became at all useful.
There is an ongoing debate about these companies drawing direct power from private plants vs going through the grid, but I can't see why big tech won't win in the end, especially in today's environment of deregulation.
I feel like "a hold my beer" version of this just accepts webhooks from your artifact registry and pre-pulls new versions of running images, or maybe images that node has seen in the last X hours
I had written the wittiest of emails, clicked 'Send', and the button just went grey. No other signals. I hit refresh, ignored the warning about losing data, autosave drafts FTW right(?!).
Absolutely, I think this would be a huge improvement. The ability to easily extract plaintext data locally would be a huge help with my personal organisation and planning.
Now I'm left trying to define/design what a "spec" for communication between humans and coding agents would look like, to power what Birgitta called spec anchored.