MangoCats

There are different ways to go about "programming" - if you're "just a programmer" that's fine, you're essentially doing window dressing for a department store, the world needs a lot of you. There are engineering aspects to software too, and if you let "just a programmer"s handle all of that, you will find out what they are lacking as soon as the engineering gets tested in use.

AI is an amplifier.

So very much this ^^^.

If you put in the same time and effort creating software using AI that you would have put in coding by hand, in my experience you get better software, much more thorough documentation and automated testing, and fewer "oops" moments down the line. Not perfection, but better.

If you just give a loosely specified prompt and take the first functional looking thing that comes out, you can get code 10x faster than ever before, and it's going to be a 100x bigger mess to maintain.

A rule of thumb (aka useless constant applied to imaginary metrics) that my colleagues and I have found is: 80%. Work on an assumption that what you get back from each AI pass is about 80% good or right. Work to identify the 20% that needs more refinement, do another pass, now you're up to 96% good - and honestly probably already better than most first pass ready for a pull request code we used to submit 2 years back. Do a third pass on that and you've probably got something that's not going to give any trouble in all but some really rare cases, and you got it in about half the time you would have spent on lower quality output.

I have been trying, with limited success, to get our junior engineers to use AI to review their own code before submitting pull requests. Some do a single pass and their PRs are pretty good, one says he "doesn't believe in AI" and his code typically needs 3-4 review passes before it's even acceptable, even though he's clearly using AI to write the documentation. AI review is how they're finding all these zero day exploits in widely used products, it works, it finds maybe 80% of things you're looking for (if you keep the scope focused inside its context window capacity.) We are having slightly more success with all the junior engineers by having them submit 5-10 small pull requests per 2 week sprint instead of one big one. This not only helps human reviewers understand the bite sized chunks, it also means the AI reviews are more thorough. It also means the architectural definition steps are much more critical because review of tiny chunks misses more of the architectural level picture.

The biggest ethical question I have about using AI centers on management of management expectations. If management really thinks the human contribution value in software creation has disappeared overnight - I'd look for different management, because that ship just steered straight into an iceberg field. Some of them may pull off the Kessel run in less than 12 parsecs, but most won't.

Especially for vehicles that tow trailers and the trailer tongue weight pushes the angle of the whole vehicle up...

Of course we don't have them in the US because, unlike Canada, we have far too many drivers who would adjust them up just to be jerks blinding other drivers on purpose.

All a matter of which externalities you're willing to overlook.

80 years ago, the solution to pollution was dilution - nobody gave a flying F if you dumped raw sewage in the ocean so long as you did it far enough offshore that it didn't come back to the beach... That works when you've got a total human population under 2B and most of them aren't burning significant fossil fuels... with 8B of us and rising, and half of us capable of hopping in a jet plane for a round-the-world trip whenever we feel like it, the pollution really does start to matter.

War is one of those side effects of civilization, and I haven't seen the war yet that gives a F about what it does to the environment, beyond maybe - just maybe sometimes - not wanting to kick off global winter.

And almost all US market vehicles are not up to Canadian standards - starting with the Canadian requirement to have driver adjustable headlight elevation trim...

Total impact is the only fair comparison. Pollution from the power plants included, sewage treatment from the houses too.

That's one way to compare it.

Now, take your privileged writer status human brain and factor in all the other power required to keep it comfy in an air conditioned room, the labor required to put a roof over your head, keep your home plumbing working, make your food, deliver you pen and paper to write with - or are you using an electrically powered appliance to record and later communicate your thoughts? Oh, did you need to go to sleep for a while?

While it's true that a human brain only uses ~20W of power, it's a really specific kind of organically delivered power with all sorts of environmental requirements that we, being humans, take for granted, but in the bigger picture it's really a rare location in this universe that doesn't kill us nearly instantly - much less provide that 20W of power in a form a brain can use.

That is one positive aspect of a road trip, particularly a solo road trip - long periods of dull required attention...

I believe the progress of the last year is largely attributable to the appropriate "grafting on" of these wrappers around the LLM cores.

What I see in the modern models is that you can often ask them to write a program or script to do a task and they can do that successfully much better than doing the task itself directly - once they have debugged the program it is usually 100% reliable for the specified tasks. Ask them to do those simple tasks directly and you get all kinds of creatively wrong answers.

The void definitely seems preferable to a lot of existences I have seen others enduring.