MangoCats

joined 5 months ago
[–] MangoCats@feddit.it 1 points 1 week ago

The problem is when people assume you can actually build an entire software/service architecture of any complexity just through vibe coding.

Welcome to CEO handling 101. It's an art, a very soft skill, and not for the faint of heart. I worked for a mid sized (50 employee) company once where I'd "speak truth to power" in our weekly meeting, get shot down rather enthusiastically by the CEO during the meeting, then after I and the rest of R&D left his office, he'd go out to production and have them start implementing all the concepts of my pitch - as his own ideas, naturally.

[–] MangoCats@feddit.it 2 points 1 week ago

That's a great tip: having it review the security of code that an earlier context generated.

I plan on having it write unit tests, or at least try to...

[–] MangoCats@feddit.it 2 points 1 week ago

You need to be able to read it to understand that it’s going a little off the rails.

At least 2/3 of the time I spend with AI coding is getting it to compile without errors - that's more than a little off the rails, but it's also much more helpful when you finally do get to a working example that you can look at, instead of beating your own head against the Stack Exchange archives hoping for inspiration, let it try for you.

[–] MangoCats@feddit.it 2 points 1 week ago

I have been building various things with AI coding tools for a month or so now. I rate the various engines on how far I can take them before they get hopelessly lost, unable to correct their own errors. For the best tools this seems to come after about 50 to 70 iterations of asking for small feature additions or error corrections, weaker tools (like Copilot) hit these infinite loops of fixing their errors with other errors much faster.

It's a good limit, because after 2-3 hours of AI interactive development, I can then spend 4-6 hours going through the resulting code - cleaning it up and understanding how it works. I suspect if AI were taking me farther, like 100-150 iterations, it would probably take me more like 15-20 hours to unravel the various things it comes up with - kind of a point of diminishing returns.

Bottom line: think of your project in terms of microservices. AI is pretty good at microservices. As long as the individual services are each robust in their delivery of the required functions, you're in good shape.

If it ever becomes "mystery meat," it's time to recode by hand.

[–] MangoCats@feddit.it 6 points 1 week ago (1 children)

AI coding is actually a very powerful tool, almost like a light saber. Do you notice how many amputations and artificial limbs there are in that galaxy far far away?

[–] MangoCats@feddit.it 3 points 1 week ago

Because: for $20 per month to the AI company, you can output poor code much much faster.

[–] MangoCats@feddit.it 9 points 1 week ago

For a more extreme example, look to the Principality of Monaco. Being so much smaller, it can be much more extreme.

[–] MangoCats@feddit.it 1 points 1 week ago

it can’t be that hard to have an automated lock on the door.

No, but human factors dictate: it can be that hard to use the lock properly.

out them further away.

Some places do this, other places don't have a good layout to make metal detectors a practical thing for the MRI suite.

with MRI machines costing what they do, these aren’t the prices you would worry about.

Often (depending on location), the most expensive part of the MRI suite isn't the device, but the room itself.

[–] MangoCats@feddit.it 1 points 1 week ago

The machines are actually built pretty tough for the impact. I think they're designed to resist a flying steel oxygen cylinder and just crack some plastic cover parts. One place I visited told a tale of attempting to remove the stuck O2 cylinder using a come-along and strap, but I believe they were unsuccessful and had to quench anyway to get it off.

could never calculate the price of the repair versus the value of the possibility of saving human life.

If necklace guy was being choked by his chain and quenching the magnet would have saved his life, I'm 99.99% certain that any tech I have ever spoken with would have quenched the magnet without hesitation. However, if the chain snapped his neck while dragging him across the room like being jerked in a hangman's jig, quenching is far too late to be of help - I'm pretty sure they would push the $30K button anyway, just out of respect for the dead and to make removing him slightly more dignified, also because they're not likely to get that steel ball off without quenching.

[–] MangoCats@feddit.it 1 points 1 week ago

Yeah, feature length movies will show "bad cops" on screen for a few minutes, but the ongoing series tend to shy away from anything other that wholesome upstanding proud law men and women keeping the world safe from itself.

I used to live in a neighborhood with a lot of police residents. Most of them are "good" in their own actions all of the time. All the ones I knew were "good" in their actions most of the time, but once in a while they'd go all judge-jury-and-executioner with a badge and a gun - I never knew about any coverups, but I did have a neighbor get suspended for a month with pay and a strong word from his sergeant "don't to that again..." The worst of it is that virtually ALL of them will look the other way / assist in spinning an issue to "help a brother in blue out of a jam," and they know that they have each others' backs that way, so they will do bad things because they have that confidence that they are untouchable.

[–] MangoCats@feddit.it 1 points 1 week ago (2 children)

Well, the thing is, to kill the magnetic field within a few seconds would break the machine, so they don't do that because it would up the cost of a shutdown from tens of thousands of dollars to several hundreds of thousands of dollars, and the downtime would go from several days to potentially several months.

As it is they "quench" the superconducting electromagnet, which then requires a large amount of LH2 and electricity to get going again. I have heard numbers like $30,000 to get the magnet running again, not counting lost revenue during the many days it takes to get going.

view more: ‹ prev next ›