from what I’ve heard from my software engineer friends, a decent coder with standard knowledge of CS and the language they’re using will always write better (more optimized, more debuggable, etc.) code than currently available LLMs
even if the “fraction” is closer to 1 than 0, the heavy lifting here is done by “look what they need.” vibe coders need gigantic climate destroying machines to write code that isn’t as good as what an educated programmer writes running on a burrito and coffee
A lot longer than that…Y2K was the result of corpos prioritizing doing things as cheaply as possible and kicking the can down the road for 4 plus decades at that point, and when they finally decided to fix it before it blew up in their faces, it was almost too late and the software engineers were forced to hack a solution to buy another decade, then promptly got canned when “nothing happened” (leading to Y2K10 actually causing some problems when it rolled around)
We’ll have another reckoning with this same class of error in January 2038 when the 32-bit UNIX epoch ends, and I have no doubt it’ll be a shit show with a lot of pushback against anyone trying to fix it because we “whined” so much with Y2K…
Depends on your domain. Devops is mostly a solved problem terraform is well documented and most infra follows a far more simple pattern. It’s not replacing engineers but if you aren’t a moron it can be a 5x type tool. It is extremely good diagnosing issues, parsing logs, and frankly writing well formed TF. It’s garbage at architecture and every once in a while it’ll absolutely send you a wtf were you thinking type pr. But it’s 80% good with a 20x in raw velocity.
Our team has fixed up a lot of shitty technical debt, increased automation and our deterministic scripts and workflows, and increased usable test coverage on $30/mo copilot plans.
The big problem is that sometimes it’s “good” at diagnosing issues and sometimes it’s very bad and in both cases it looks the same if you don’t have a way to know yourself.
I’ve seen some of the fodder people consider ‘well formed playbooks’ and it’s also a bit of a crapshoot there. It can speed up some tedium, but so many users get in over their heads.
Today had a junior proudly provide an untested playbook that just did everything wrong and even if it did what it purported to do, it would have been hard coded to certain things that are not what we want to do.
I’m tempted to try to calculate how much energy has been used to produce the currently and previously available library of anime popular amongst coders, because that’s a necessary resource, along with various energy drinks and snackies
a fraction is being too kind to us
from what I’ve heard from my software engineer friends, a decent coder with standard knowledge of CS and the language they’re using will always write better (more optimized, more debuggable, etc.) code than currently available LLMs
even if the “fraction” is closer to 1 than 0, the heavy lifting here is done by “look what they need.” vibe coders need gigantic climate destroying machines to write code that isn’t as good as what an educated programmer writes running on a burrito and coffee
Unfortunately we live in day and age when corporations prioritize quantity over quality.
And that age is going to be very short as it will end with flaming hacks and downtime.
Been suffering the hacks and downtimes for over two decades waiting for the day when corpos come around on this.
Hard to continue holding out hope.
A lot longer than that…Y2K was the result of corpos prioritizing doing things as cheaply as possible and kicking the can down the road for 4 plus decades at that point, and when they finally decided to fix it before it blew up in their faces, it was almost too late and the software engineers were forced to hack a solution to buy another decade, then promptly got canned when “nothing happened” (leading to Y2K10 actually causing some problems when it rolled around)
We’ll have another reckoning with this same class of error in January 2038 when the 32-bit UNIX epoch ends, and I have no doubt it’ll be a shit show with a lot of pushback against anyone trying to fix it because we “whined” so much with Y2K…
Sorry… Don’t drink and rant…
They always did this. Now they are just doing it faster.
Depends on your domain. Devops is mostly a solved problem terraform is well documented and most infra follows a far more simple pattern. It’s not replacing engineers but if you aren’t a moron it can be a 5x type tool. It is extremely good diagnosing issues, parsing logs, and frankly writing well formed TF. It’s garbage at architecture and every once in a while it’ll absolutely send you a wtf were you thinking type pr. But it’s 80% good with a 20x in raw velocity.
Our team has fixed up a lot of shitty technical debt, increased automation and our deterministic scripts and workflows, and increased usable test coverage on $30/mo copilot plans.
The big problem is that sometimes it’s “good” at diagnosing issues and sometimes it’s very bad and in both cases it looks the same if you don’t have a way to know yourself.
I’ve seen some of the fodder people consider ‘well formed playbooks’ and it’s also a bit of a crapshoot there. It can speed up some tedium, but so many users get in over their heads.
Today had a junior proudly provide an untested playbook that just did everything wrong and even if it did what it purported to do, it would have been hard coded to certain things that are not what we want to do.
I’m tempted to try to calculate how much energy has been used to produce the currently and previously available library of anime popular amongst coders, because that’s a necessary resource, along with various energy drinks and snackies