cfeduke

I have been thinking about trying this approach. We really need something that's in-between, right? There's going to be code that is boilerplate implementation, and I don't need to drive that - like we have, in the before times, relied on macros and what not to do that work. But then the interesting logic, seeing the suggested implementation, copying or working from that. That's the sweet spot.

I've also been thinking about the partner programming craze phase our industry went through. I write the test, you write the code; well I write the test, LLM satisfies with code. (Then we have less of these weird LLM generated test cases that test _nothing_. We can also use the LLM to suggest tests to complete coverage.)

These would be slower to work this way, but the end result is:

1. humans still learn 2. you have a good grounding in how everything has been written

Perhaps I'm just daft or slow, but I'm not 10x-ed by LLM usage. It's precisely because the details matter. (And yes, I read the article and it's lamenting the loss of low level machine-level details.) I read the LLM output, it slows me down. I challenge the LLM output assumptions, that slows me down. I stop to step away and think, it slows me down. I cannot run a bunch of simultaneous prompts and supply this same level of mental context to all of them, because my brain works best when I treat it as single-threaded. My experience with this approach to using an LLM has been, so far, positive.

What I have noticed as I've migrated to newer models is that the assumptions made are incorrect less often. But if I don't pay close attention wrong assumptions can still be made. Cross cutting concerns are lost, or written in such a way as to be useless.

So, the loss of details, to me, would be my own laziness in not performing due diligence.

The example could be hyperbole, but Home Depot and Lowes both offer a wide selection of "smart toilets" and if we think "oh this is just a weird niche thing that will never catch on" let's remember how difficult it is to not purchase a Smart TV when television shopping these days.

Depending on where I park in the city, I have to install a different parking app. And create an account, and pay with a credit card via the app. There was a time, however brief, when some of the parking meters just accepted credit cards, or get this, coins.

This is what happens when a large number of people claim they "don't seem to feel the pain" and comply with the data broker's wishes. We all get stuck in the data brokers web, or we have to break the law to park on a public street.

I bought a Model 3 in 2018, a Y in 2020, and another 3 in 2024. The end user design has only continued to get worse on various aspects of the car. Regarding non-safety issues, living in the northeast and mid-Atlantic, the door handles freeze shut during the winter and become impossible to open from outside of the car.

But why continue to buy these poor end-user design experiences, you think? My car maintenance costs since 2018 has been a gallon of windshield wiper fluid and new tires. So I deal with poor design decisions.

But the cup holders in the latest Model 3 may be my breaking point.

> Generally speaking, for most people, bills go up as they age (kids, health, yada-yada).

To a point yes. There was a time when you could realistically pay off your mortgage before you were fifty, and for some people maybe this is still the case. College expenses are another consideration, just depends on how much you as a parent are going to shoulder those costs compared to grants/military/self earn.

For myself, costs have lowered and I'm able to donate more money to charity. So if you can swing a bigger paycheck and you're motivated help others I think it's worth doing so.

From AWS pricing:

> Per 10,000 API calls

> $0.05 per 10,000 API calls.

So imagine you have some number of cron jobs which require a bunch of secrets and these things fire every minute or 30 seconds or what have you. You could save as much as $0.25 a month!

Okay I guess I've just had a different experience entirely. Maybe I'm jaded by hallucinations.

The code ChatGPT generates is often bad in ways that are hard to detect. If you are not an experienced software engineer, the defects could be impossible to detect, until you/ChatGPT has gone and exposed all your customers to bad actors, or crash at runtime, or do something terribly incorrect.

As far as other thought work goes, I am not consulting ChatGPT over, say, a dietician or a doctor. The hallucination risk is too high. Producing an answer is the not the same as producing a correct answer.

Tesla uses independent body shops they certify, I know this because I've used one as a result of a deer accident. The service centers do not handle beyond some level of damage.

My personal experience so far with Tesla specifically - and this is not to say they are doing the right thing in regards to parts or anything - was when my wife hit a deer and a bunch of the driver's front side of the car had to be replaced was that it took six days. Of course the bill insurance covered was around $12K which is just insane (headlight, hood, fender, panel, side mirror, camera). The timeline to repair was probably because the Tesla density for my area (around Richmond, VA) is not high like it is in places such as California.

Other than that, which was $0 out of pocket, I've had my Model 3 for six years in July and almost $0 in parts or service. I replaced the 12v battery which I had to buy for $75 and tires twice. This way more cost effective than my Lexus (around $4,000 in repair service over 5 years, not counting tires) and Mercedes (around $3,000 in repair service over 2 years, which - not counting tires and I had these AMG rims that were wider on the rear tires so tire replacement had to happen early). So its hard for me to complain about Tesla, but I can see where for other people who have had issues where there are a lot of Teslas on the road could be an issue.

If its tech and they want a 30-45 minute interview with live coding on something like hackerrank - especially if whatever brain teaser they've chosen has absolutely nothing to do with the field they operate in - I'd put the chances around 80%.

> I don't see how AI, quantum and block chain are at all equivalent.

It's not that there is any claim to equivalency, its that these are the technology trends that are most useful - the trend itself, nevermind any sort of usable technology - for those who grift.

For all these "it is better" points, it still doesn't even begin to outweigh the "you get to spend time with your children" point. This is the most important part of child rearing and once they've moved on you'll be thankful you spent your time with them instead of... whatever all that income/societal optimization stuff is. You get to raise your children once.

> browser search bar and get perfectly good answers

That depends. If your search engine is Google, you'd get things like "The best 17 AAA games by budget to buy in 2024" or "22 triple A games for a tight budget in 2024."