I've had a ring camera for several years. Historically I've been mostly satisfied with it, but lately they are adding some features that are pretty annoying.

The worst is that they've been adding neighborhood alerts and other proximity alerts, with categories for traffic and weather and lost pets and things like that. Today I got a "community alert" which was actually an advertisement for a local animal shelter. I don't have anything against animal shelters, but my motion detector camera alter is not the correct venue for this message. It's clear that amazon is trying to muscle in on Nextdoor. I don't use Nextdoor. I find it to be like facebook, full of cranks and advertisements and nosey annoying people.
So now I had to wade through a few pages of menus to find where to turn of this new annoyance. Obviously, if I could I would opt out of all new features.

The other annoying thing is that they turned on some AI evaluation of what the camera sees. So I was getting messages like "there's someone with a garden hose on your lawn" or "a person is carrying a cardboard box". There were a few things wrong with this

• I didn't sign up to have this and it slows down the alerts so they are up to 30 seconds after the motion is detected
• The AI sometimes made errors, especially at certain times of day where it misidentified different things in the yard (for example, some place marked by shadow was interpreted as a sidewalk when there isn't a sidewalk there). This happens of course because the AI doesn't know anything about my property, it evaluates everything from scratch each time it looks at an image.
• The ring app started bugging me with upselling messages to pay extra for the AI messages

So yeah. I just wanted to vent about the enshittification of this thing. I'm also aware of the privacy issues of ring cameras and how they're going to use the "pet finder" functionality to keep track of everyone. But this rant isn't really about that more important stuff, just the frustration of how these tech companies won't just leave anything alone because they have different goals than us.

I probably triggered some PTSD right there.

Was just in a meeting at work, where we listed off everything that makes software development hard and slow. An excersize for the thread would be to replicate that list. It turned out that Claude helps with like 1/5th or less of it....especially in a collaborative environment.

So, the situation we're now encountering is that random business areas can vibe code out something, tell nobody, throw it in AWS, have it become a critical part of a business process that fails when they quit, and nobody even has access to look at what was made.

It gives me comfort that in about 5 years there will be a new surge in demand for programmers to reign in all the rogue applications that need shutdown because of the immense risk to continual operation of a company, from data leaks to broken payroll.

It'll be Y2K all over again.

For a long time programmers have had two types of program verification tools, static analysis (like a compiler's checks) and dynamic analysis (running a test suite). I find myself using LLMs to analyze newly written code more and more. Even when they spit out a lot of false positives, I still find them to be a massive help. My workflow is something like this:

1. Commit my changes
2. Ask Claude Opus "Find problems with my latest commit"
3. Look though its list and skip over false positives.
4. Fix the true positives.
5. git add -A && git commit --amend --no-edit
6. Clear Claude's context
7. Back to step 2.

I repeat this loop until all of the issues Claude raises are dismissable. I know there are a lot of startups building a SaaS for things like this (CodeRabbit is one I've seen before, I didn't like it too much) but I feel just doing the above procedure is plenty good enough and catches a lot of issues that could take more time to uncover if raised by manual testing.

It's also been productive to ask for any problems in an entire repo. It will of course never be able to perform a completely thorough review of even a modestly sized application, but highlighting any problem at all is still useful.

Someone recently mentioned to me that they use vision-capable LLMs to perform "aesthetic tests" in their CI. The model takes screenshots of each page before and after a code change and throws an error if it thinks something is wrong.