For me, the best use of AI is making bespoke software connecting systems and devices that have no business being connected but I find value in so I can have a unique interface for all my tech and hobbies. Not sure how that gets translated to the everyday man but it sure isn't "bring me food".
Agents are great for that middle ground between just doing it manually and creating an automation to do it. Which strikes me as yet another reason AI is so well suited to software development tasks, but hard to find useful applications outside of software development.
idk, I develop a lot of connected systems: Pis, Macs, lights, Google speakers, custom ESP32 boards. Understanding the capabilities and communication methods to pool them together is still very much part of what I do. If you're thinking one prompt -> production via AI, sure. But I don't think we are anywhere near that because there are so many moving pieces which still require human sign off: legal, design, QA, etc. To me, it just shift ups the level of understanding rather than replaces it.
Seems like an odd criticism given that programming has always been about abstraction. But sure, I don’t know tree-level details (functions) but I also wasn’t doing leaf-level (bits) understanding because that became obsolete. Now I’m on forest level and expanding to eco systems.
You can always know more but at a certain point, after you’ve built enough validation and safe guards, you find it’s not the best use of your time and the things you can make beyond your specialization is quite remarkable.
Also, I think the toothpaste isn’t going back in the tube with this
The internet is full of people doing the “AI = compiler” comparison and it’s just wrong.
Maybe on a really small scale they can resemble a compiler because the number of possible outcomes is so small that it’s nearly deterministic.
But at any larger scale AI will not be deterministic anymore and at that point it will be relevant what the resulting code looks like. Because it can and will be slightly or very much off from your instruction.
If all inputs match a spec then why does it matter that the LLM is non-deterministic? I agree we might not be there yet, but the timelines for progress is shrinking and we are more likely to get there in a matter of months than not.
I figure out how to do something, wrap it in a bunch of functions, and then kinda just use it. If it just keeps doing what it should, I may kinda forget how it works. But I don't forget that I made it, and that I understood it, that will never not have happened. So in a way, I am able to "forget" some things because I still know I knew them. And I trust that programmers who write programs that I dream about writing also know what they're doing.
With LLM, you accumulate stuff with from knows where, ultimately fished from a vast ocean named question mark, by whatever turns of phrase you and involved agents happened to use, and what the temperature was at that moment. Which is of course where all the harnessing and looping and running code on the output comes in, but still, ultimately you have no idea. Which is fine for prototypes, but long term? Good luck.
I can look at mystery code in the work app from five years ago, and know that I wrote it without any memory of doing so. I can remember the warty bits and pitfalls, maybe not in great detail but enough to jog the memory and I'll be more effective while working on it than someone seeing it for the first time.
I guess I'm just lost on things not being solved to a degree. Maybe its that I'm an iOS engineer where things are so locked down as far as goals and efficiencies that AI doing the work is verifiable by running the program, setting up some pre and post verification of code, and writing tests that look for certain edge cases. To be frank, it just seems like a trust thing. I trust it to the degree I am willing to to verify it.
“The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise.” — Edsger Dijkstra
I've thought a lot about this quote, and the best abstractions I use are absolutely this. I love array indexing as an abstraction, but in the back of my head I have pointer + index * size. I like having the kernel do memory mapping, but I know there's a buddy allocator and TLB cache there.
I think the core functionality of human cooperation boils down to getting ideas from one mind to another or many. In that, I think AI is a boon for people with limiting abilities such as learning disabilities, low language fluency, or generally poor writing skills. It evens the playing field for new and interesting ideas to spread. I can't help feeling, sometimes, this is about people who excelled at something demanding they still have their place at the top. High literacy such that you can discern LLM Voice is quite an accomplishment but blanket dismissal reeks of privilege.
That being said. Yes, I hate some LLM Voice moments too and still sometimes judge people for copy and pasting, expecting others to do the comprehension when it seems they haven't done it themselves.
I highly disagree, though I admit I am one of those towards the top of literacy and cognitive skills. I absolutely enjoy when someone uses LLMs to learn. However, I don't think that's what we'll be seeing.
Look at programming. What's happening there is we are having agents produce 10-100x the code to where people give up on reading it and just hit OK. Look at math. Plenty of people there want to learn from the LLMs and all these crazy new math proofs. But those are the people who will probably be out of a job soon because the money in math is in producing proofs, and that's now an LLM-exclusive job.
I think LLMs are weird in that the first order effects are those of an incredible and amazing tool that anyone can learn things from, but the second order effects are going to be the exact opposite - people giving up on bothering with ideas. Even at my job, which is one of the few that has not gone crazy with AI, anytime I ask anyone a question, all I hear is "have you asked Claude?". There's no communication anymore, no pushback, no struggle. I worry that one day we'll look around and realize we've built an entirely separate second civilization of machines and robots that acts more like a neighboring country than a tool we can use to build humanity up.
I worry that--while they can be a strong fuzzy search tool-- their teaching ability falters because teaching involves possessing a theory-of-mind for the student and trying to figure out what will change how they think. A good teacher doesn't just present you with relevant facts, they try to figure out how you're reaching conclusions.
Note that I'm excluding propoganda-style "teaching" here, where a model just insists you're wrong and that all the cool kids are doing it etc.
Given that LLMs are non-static and can be honed, why isn't it seen as value that you pass your theory-of-mind to the the LLM so that it can present information that is the most effective for your ability to learn?
In a contest between the "supercharge my education and skill development" use and "let me be as lazy as possible" use of AI, it should be pretty obvious which will win out at the end of the day.
It is not any different from knowing the difference between good writing and bad. I can't help it that I have taste and preferences. I can avoid telling you yours are wrong. But I don't think this is a minority position and nor is it different from people who reflexively hate AI "art" or music
Nothing wrong with having preferences, dismissing people outright based on them is problematic if you're rejecting the ideas because of the medium and method shared.
This has nothing to do with medium or method. It has to do with written words that aren't worth reading, and there is nothing wrong with expressing your opinion when you come across that. If something is really well-written, no one is going to dismiss it for being generated because it won't be possible to notice that it was generated.
A writer who can't recognize LLM voice isn't a good writer, just like a writer who doesn't do research or fact checking isn't good. It has nothing to do with method, its about skill and work effort.
That's the same thing. Your filter is the quality of composition such that if it doesn't meet your expectations, the message is not worth knowing. My point is that the message, the idea, can still be worth communicating and not accepting it based on the writing is dismissive.
I really don't understand some of the comments here. I've honestly been automating so much of my work that I spend most of my days working on personal projects and checking in on what's being done on my behalf by AI. This, of course, after spending a few weeks setting up validation tools so I can trust the output.
Same. Once I actually tweaked my agent to do all the same work I used to do by hand, I now do so little work that I often try to think of ways to performatively imply that I’m working hard out of fear that maybe someone will catch on and I’ll just get fired out and replaced with my agent once and for all.
A neat trick I’ve found is that I can just invent random work for myself in the form of building custom tools and skills for various workflows and write it off as research.
But someone in the same business field as yours, who, instead of spending time on personal projects, is working on the business itself, will be ahead of you.
Maybe. I've been able to spin off crash fixes, CI/CD improvements, and even demoing my personal projects as AI exploration. So my visibility is at an all time high.
As a life long and continuous Apple user (and iOS SWE), I recently got a $150 Samsung Android tablet that I can use as a claude interface. It can take in voice commands, and create new builds of itself on a network Mac. So I can essentially have whatever screen or interface I want for any given moment. Right now I'm tuning my motorcycle with an OBD bluetooth device and recording engine behavior on rides.
If you don't use the router they provide, they literally cut your line. They don't say anything about this or ever explicitly clarify this, but they will cut your line, their customer support will accuse you of having bad equipment, and then even when you connect their equipment, the line will still be cut until you call them and have them reconnect it. Once they have, your own equipment will work again too, until they notice and cut the line again. It's ridiculous.
You can, however, use their equipment as a dumb modem and insert your own router downstream. It thankfully supports DMZ to expose your router directly to the internet without NAT. I use Ubiquiti.
I find that fascinating because I was able to get Claude to jailbreak my Kindles and add them to my tech ecosystem at home. I also was able to get it to use jailbreaking hacks on my Spotify car thing and implement some alternative ways for my raspberry pi to drive it.
reply