ProbablyBaysean

I call it ag-gnorance . Aka arrogant ignorance

By chance have you read the book permutations?

If you live in the florida Everglades then that would be pretty impressive. The global landscape has had increased nuclear proliferation, so by your analogy, its like having to pet several alligators each day and having a track record of 0 alligator attacks.

The UN if defined as having been formed to prevent nuclear war under the MAD (mutually assured destruction), had been 100% effective since it formed.

What about while you were sitting/squatting?

The video "the count censored" is quite good.

I built a full stack SaaS that is deployed at my work. It is exposed to the internet and I have only used pentesting and asking the ai "what is this" and "fix this" and feature requests.

It has awful context limitations. Saying "do this" means it overfills context halfway through and loses the nuance as it tries to restart the task after summary. I dont trust it to make a todo list and keep to it. I have to work with the slightly long term "markdown files" as memory.

I have had good progress when I say "add this pentest_failure/feature_request to an open items list markdown file" then the ai finds context defines the issue and updates the file. Rinse repeat. THEN I say "I want to make a refactor that will fix/implement as many of the open items list issues as possible, can you/the_ai make a refactoring spec". THEN I carefully review the business logic in the refactoring spec THEN I tell the ai to implement the refactoring spec phase 1 then i test then j say do phase 2... etc.

Design concerns like single source of truth, dry, separation of concerns, and yagni have come up. I have asked about api security best practices. I have asked about test environment vs production.

I developed without git, and the sheer amount of dumb duct tape code made by no short term memory ai exposed by pentesting was infuriating, but I got a process that works for my level of understanding.

Ai Skills, rules, etc are still not quite clear to me

So far, I have made a full stack server on a rpi from only ai and pentesting. It is deployed (live and used by my coworkers as a part of their workday). I intend to open source it once I understand more about git.

I recently have made one pull request on one project that js very well maintained and I indicated that I used ai and it is really eye opening to see what good development/maintaining looks like.

I am currently doing a deep dive into each of the feedback notes (left by a collaborator). I am by no means fast as I'm trying to max my learning from each scrap of interaction and error. Several concepts are hard for me to remember well so I use my high level memory and commands to the ai each time they come up.

I can walk through tricky logic.

I can pentest and determine issues or if a solution works.

I dont know what is important. I dont know how to rebase git commits and get a pat token unless ai is holding my hand.

I right now only vibe code but I then deep dive through the finalized commits. I am not a programmer by trade and at best I'm a sloperator.

I think my code contributions are helpful.

If i had a vaccume and a carbon nanotube rotating such that the ends are moving at the speed of light, and another going the opposite direction (no net rotational inertia outside the device), I would have a dimensional anchor as moving it would cause spacetime to exceed the speed limit.

Voila, I just created a sci-fi plot device

A quick quip is: I dont suppose you own curtains? Humans have a harder time conceptually thinking of privacy like curtains.

Please dont insult the intelligence of a muppet