LLMs have single handedly turned the hardest part of this job into entire job. The hardest part of this job is troubleshooting, maintaining and developing on top of an unfamiliar code base. That's not a new experience for anyone who has lived the production code life. One of the first production engineers I was tutored under used to love to say, "the code should tell you a story."
I love C. I came up on C. But C does not tell you a story. It tells you about the machine. It tells you how to keep the machine happy. It tells you how to translate problems into machine operations. It is hard to read. It takes serious effort to discern its intent.
I think any time you believe the codebase you're developing will have to be frequently modified by people unfamiliar with it, you should reach for a language which is both limiting and expressive. That is, the language states the code intent plainly in terms of the problem language and it allows a limited number of ways to do that. C#, Java (Kotlin) and maybe Python would be big votes from me.
And FYI, I came up on C. One of the first senior engineers I was tutored by in this biz loved to say, good code will tell you a story.
When you're living with a large, long lived codebase, essenti
I guess I'm very confused as to why just throwing an LLM at a problem like this is interesting. I can see how the LLM is great at decomposing user requests into commands. I had great success with this on a personal assistant project I helped prototype. The LLM did a great job of understanding user intent and even extracting parameters regarding the requested task.
But it seems pretty obvious to me that after decomposition and parameterization, coordination of a complex task would much better be handled by a classical AI algorithm like a planner. After all, even humans don't put into words every individual action which makes up a complex task. We do this more while first learning a task but if we had to do it for everything, we'd go insane.
There are many hopes, and even claims, that LLMs could be AGI with just a little bit of extra intelligence. There are also many claims that they have both a model of the real world, and a system for rational logic and planning. It's useful to test the current status quo in such a simplistic and fixed real-world task.
The sneering and nihilist tone is very off putting. But not nearly as much as the boomer brained conception of the world's information model pre 2004, which was not nearly as good as those who invoke Murrow and Cronkite believe it was.
I guess maybe the tone would be less noxious if the core coceit of the satire felt more legitimate. I mean, Wikipedia was kind of a shit show back in the day. It's had 20 years of maturation which is more what makes it useful today.
And yes, the media is full of blatant and bald faced lies but is that worse than the credulous and uncritical way the media basically endorsed the war in Iraq?
I get that it's a joke but the joke kinda only works if there's some truth behind it. And I just don't think there is here. I think people are lamenting old media now, not because the information sphere is genuinely worse today but because it was a comfort to have a consensus in public opinion regardless of how true that consensus was.
A stream of linguistic organization laying out multiple steps in order to bring about some end sounds exactly like a process which is creating a “plan” by any meaningful definition of the word “plan”.
That goal was incepted by a human but I don’t see that as really mattering. We’re this AI given access to a machine which could synthesize things and a few other tools it might be able to act in a dangerous manner despite its limited form of will.
A computer doing something heinous because it is misguided isn’t much better than one doing so out of some intrinsic malice.
This is a phenomenon I call cinetrope. Films influence the world which in turn influences film and so on creating a feedback effect.
For example, we have certain films to thank for an escalation in the tactics used by bank robbers which influenced the creation of SWAT which in turn influenced films like Heat and so on.
> Gang leader Robert Sheldon Brown, known as “Casper” or “Cas,” from the Rollin’ 60s Neighborhood Crips, heard about the extraordinary pilfered sum, and decided it was time to get into the bank robbery game himself. And so, he turned his teenage gangbangers and corner boys into bank robbers — and he made sure they always brought their assault rifles with them.
> The FBI would soon credit Brown, along with his partner-in-crime, Donzell Lamar Thompson (aka “C-Dog”), for the massive rise in takeover robberies. (The duo ordered a total of 175 in the Southern California area.) Although Brown got locked up in 1993, according to Houlahan, his dream took hold — the takeover robbery became the crime of the era. News imagery of them even inspired filmmaker Michael Mann to make his iconic heist film, Heat, which, in turn, would inspire two L.A. bodybuilders to put down their dumbbells and take up outlaw life.
> we have certain films to thank for an escalation
Is there a reason to think this was caused by the popularity of the films and not that it’s a natural evolution of the cat-and-mouse game being played between law enforcement and bank robbers? I’m not really sure what you are specifically referring to, so apologies if the answer to that question is otherwise obvious.
Maybe this is why American society, with the rich amount of media it produces and has available for consumption compared to other countries, is slowly degrading.
The point is that we do not need this land. There is plenty of land all around the United States that is "habitable". And given the trend of birth rates and urbanization there is virtually no reason to go destroying fragile and unique ecosystems just so people can satisfy some compulsion for a manifest destiny of occupying every available square foot of this planet.
> if you’re a fantasist thinking we should be living in a Bronze Age utopia.
Bronze Age people were smart enough to live in places with easy access to fresh water, so they're demonstrably wiser than whoever came up with this proposal.
This is a false dichotomy. The choice isn't between total exploitation of the biosphere and poverty. Nowhere did I say that European development should have been minimized. I simply said the example of European development was not a good argument for attempting to transform the environment of the American West.
Let's look at the chain of argument. The poster was countering an assertion that humans have created massive ecological turmoil by seeking to fundamentally reshape the Earth. Their counter was that Europe was once forest and swamp. I can only assume they meant that we take for granted that the present condition of Europe is good and because it was once mostly "just" forest and swamp that Europe demonstrates that these transformations are acceptable or even preferable and therefore we should do them.
I think this is a bad argument because it contains many assumptions and implications which I think are false.
Assumptions:
#1 The magnitude of exploitation of Europe was necessary to achieve modern life.
#2 The development of modern European life occurred on an ideal or preferable timeline and things would not be better if this process had been gentler to the environment and taken an additional 1,000 years.
#3 The ecosystems of the American West are not more unique or prized than the temperate forests of Europe and their loss represents a similar loss therefore justifying the trade off.
#4 Wilderness, despite its increasing scarcity is not more valuable today than it was 1,000 years ago.
#5 Exploitation of the American West would have a similar economic and developmental impact as the exploitation of primeval Europe and therefore represents a worthwhile trade off.
I don't think any of the above should be taken for granted.
As a life long resident of the American West, I can imagine few ecological crimes more horrifying. This is one of the most unique geographies on this planet. The life here is thoroughly adapted to a fragile balance of long want and occasional abundance. Everywhere you "terraform" would obliterate that balance. The application of the word itself is obtuse. How can you make more Earth like what the Earth itself made? I suggest that you take your infrastructure projects and apply them where people already live. The damage has already been done there. And those places have an elasticity of life due to the high amounts of water that let them bounce back at some point. Instead I suggest for the West we take a page out of Edward Abbey and simply marvel at its incredible uniqueness and beauty.
There are bad examples of land use like agricultural monoculture and suburban lawns but if you compromise with nature it can be a thriving ecosystem albeit one designed to benefit humans.
It's a matter of water being a great place for carbon based chemistry to occur. Why carbon? Because it is so dynamic. It readily forms complex molecules which interact in interesting ways.
Looking at other forms of chemistry we don't see much as naturally varying as carbon. Though I have heard some chemists and biologists hypothesize about sikicon based life. At high temperatures it forms the kinds of dynamic connections that carbon does.
I love C. I came up on C. But C does not tell you a story. It tells you about the machine. It tells you how to keep the machine happy. It tells you how to translate problems into machine operations. It is hard to read. It takes serious effort to discern its intent.
I think any time you believe the codebase you're developing will have to be frequently modified by people unfamiliar with it, you should reach for a language which is both limiting and expressive. That is, the language states the code intent plainly in terms of the problem language and it allows a limited number of ways to do that. C#, Java (Kotlin) and maybe Python would be big votes from me.
And FYI, I came up on C. One of the first senior engineers I was tutored by in this biz loved to say, good code will tell you a story.
When you're living with a large, long lived codebase, essenti