That's a good question... => I didn't think about this, I don't know the answer yet.
That's a great question! => I can tell you understood what I explained and used that understanding to reach the next step of reasoning just like I did.
> If I do ask an LLM another question about something small it will offer solutions but doesn’t offer the solution I think makes sense in the architectures I’ve written.
This is my experience as well, and I've been using Claude Code a lot.
Extremely impressive tools, but they're like fast food. They will solve your immediate problems quickly and cheaply, but you're going to have issues on the long term if that's all you use.
Have you tried drilling into the reasoning when this happens? This is why I usually leave it in "Plan Mode" and when it proposes a solution that seems unusual or unexpected, I point out why I think it is and ask it to justify it's position.
Sometimes I get the "you're right!" response, but often it will also explain why it made the decision it did, and it's rational enough that I accept the new approach.
It's still very much like a junior dev in this way - pretty good at 'just make it work', pretty good at monkey-see-monkey-do, and occasionally surprises you with something novel (to you).
> Sometimes I get the "you're right!" response, but often it will also explain why it made the decision it did, and it's rational enough that I accept the new approach.
I think this is kind of what I’m worried about. Referencing Karpathy, an LLM can basically convince any one of anything. Doing this enough times and your opinions just become the LLM opinion. Same with problem solving approaches. I see this for myself so I reserve time to formulate my own solutions. Maybe my solutions are worse but at least I’m training the muscle that may lead to me outperforming the LLM in specific spaces
> LLM can basically convince any one of anything
This and revision to the mean I think are real problems
I've found myself on more than one occasion just stepping away and needing to really sit down and think and to not ask an LLM until I have a clear idea of what I want to do
The one thing that bothers me is that one process I really used to run is thinking in code, slowly sketching out a solution until it had the properties I wanted it to have
I find myself not really engaging with this at present and it really bothers me, I've been trying to figure out how to get back into doing it again because I think the most differentiated and interesting ideas and thinking I had were usually shaped by going through that process
However so far I've found working with LLM's just doesn't jive with that thought process and several months into using them I'm still figuring out how to go back to doing that
Fast food might be the right approach if it's a business that prefers speed to maintainability, and they might move towards that with LLMs. I wish more developers would go with it instead of fight it. It's not like it's a personal failure you can't convince the business to slow down and prefer quality.
The quality of the craft can live on in open source and personal projects.
More like developers who give quality away for free then are left wondering why businesses who make millions still end up squeezing the life out of them.
It's true for all automation we do get more comfort. We build systems so that we humans have as little struggle as possible, not realising that struggle is the only reason for existence. By eliminating it, we are erasing ourselves from this world.
This kind of argument flies in the face of the fact that plenty of inherited rich people seem to lead very happy lives. Of course, they do find things to struggle with, but it's much more pleasant to struggle to score 72 at the golf course or to outbid a rival for a piece of contemporary art than to struggle for basic needs.
I can live a happy life without struggling for basic needs and without playing golf all day long. If you strip off every obligation from life, then you exist, not live.
Facing challenges and overcoming obstacles, friends and family is what makes me happy. When you’re rich, most people only care about your money, not the person you are. And I think that’s exactly what a happy life is about.
I guess to each their own. But in the little free time I have as a non-rich version, I like to face low-stakes challenges I myself choose, e.g. in my case those currently mostly are learning Chinese and learning to play a musical instrument. Those still provide obstacles, difficulties, the feeling of progress and moments of success/failure, but I can do them at my own pace and with no serious consequences if I fail.
I can imagine I could be perfectly happy with a life full of challenges of that kind, instead of being forced to work at given scheduled times which often imply I spend less time with my son than I would like, including days I don't feel like it, and including boring tasks (I love my job, but like almost every job, it also has its paperwork, pointless meetings, etc.), knowing I depend on that work to live.
In short, I think we all do need the challenge, the struggle, the successes and the failures, otherwise life would just be boring and pointless. But I don't think we (or at least I) need the obligation component and the high stakes.
What you mention about the rich attracting people focused on money rings true, but it would be moot if AI led us all to lead lives more similar to the rich, which was the point here. (Of course, there's also the issue of whether there is widespread or unequal access to AI, but that's another story...).
It's fairly easy to be submarine rich, and fly completely below the radar. Just brush off questions about your work with vagueness. If you're not flashy, nobody will suspect you're rich
i agree, but i doubt anyone on hn is struggling for basic needs. so the struggle is almost always fun, and i think that goes for most white collar jobs. it's a fun struggle. getting to the office, doing some chores, and that's something AI is slowly killing off
Automation is also for reducing drudgery - the work that prevents us from meaningful struggle by taking up resources that can be better applied elsewhere. Not all struggle (or pain) is created equal.
I wouldn’t count on reduced drudgery. The assembly line automated many movements needed for manufacturing. But which work involved more drudgery—-craftsman-style car production or standing on an assembly line at Ford?
With any new technology, subsequent drudgery depends on the technology, its concomitant economics, and the imagination of the people using it.
Being inquisitive doesn't equate to loving, or needing, struggle in my brain. Also, struggle differs for many people. Running a half marathon was a struggle for me, but I can't compare it to a family who is struggling to pay bills.
If we take Maslows hierarchy of needs, me running a half marathon is self actualization. Something I'm privileged to be able to do. A family struggling to put food on the table is still on the Lower tier of the pyramid.
You're wasting a ton of tokens doing that though. Right now you don't realize it because they're being heavily subsidized, but you will understand the point of have good orchestration and memory files when you will have to pay the real cost of your use.
Cost cannot go up, only down with time (with occasional short term fluctuations). Competition, including open weight models and consumer hardware (ie upcoming M5 Ultra) keeps moving ceiling of what you can charge down.
Company pays for company’s tokens, so company’s problem, not mine. I am happy to skill up and avoid overusing tokens for my personal sub, but if it’s getting results then I couldn’t care less how much my employer has to pay for it. They’re begging me to use it in the first place anyway.
> You're wasting a ton of tokens doing that though.
My time is worth more than tokens. I’m thinking of maybe creating some .md files to save me time in code review. If I do it right, it’s going to cost more in tokens because the robots will do more.
I think their current goal is to capture as much market as they can while they still have the best models, their only moat. Look at Anthropic, they are clearly trying to lock their users in their ecosystem by refusing to follow conventions (AGENT.md etc) and restricting their tools exclusively to their own services.
reply