Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Greg Knauss Is Losing Himself

shapeof.com

Post reply on HN
Print view View original

51–60 of 63 posts

Re: Greg Knauss Is Losing Himself

#51

Post by wartywhoa23 »

slibhb wrote: post #19

> It was a nice little feature that I knew exactly how to do, but I hadn’t prioritized getting done yet because there were a bunch of other things on my plate. But with a little assist, it was quick to implement. Exactly how I feel. AI has allowed me to work on projects that I've wanted to work on but didn't have the time/energy for.

> AI has allowed me to work on projects that I've wanted to work on but didn't have the time/energy for.

So let's flood the world with projects nobody, including their authors in the first place, cared for enough to dedicate time and energy to.

Re: Greg Knauss Is Losing Himself

#52

Post by MarcelOlsz »

cc-d wrote: post #49
MarcelOlsz wrote: post #31

Earlier quoted context omitted.

This song bangs, looping this all day. What a throwback. Reminds me of ytcracker/digitalgangster days. Also reminds me of Das Racist. Thanks for posting this lol. Love that grime-ish electro beat. Can you email me? Would love to chat/get more tunes from you.

Sure what is your email? Mine is ccarterdev@gmail.com I watch this comment more closely though :) Mob currently controls my email

Emailed! Mines in my profile.

Re: Greg Knauss Is Losing Himself

#53

Post by braebo »

gtowey wrote: post #21
bee_rider wrote: post #16

Earlier quoted context omitted.

> Because LLMs don't understand things to begin with. Ok, that’s fair. But I think the comment was making a distinction between the big picture and other types of “understanding.” I agree that it is incorrect to say LLMs understand anything, but I think that was just an informal turn of phrase. I’m saying I don’t think there’s something special about “big picture” information processing tasks, compared to in-detail i…

I would say that it's very germane to my original statement. Understanding is absolutely fundamental to strategy and it is pretty much why I can say LLMs can't be strategic. To really strategize you have to have mental model of well, everything and be able to sift through that model to know what elements are critical or not. And it includes absolutely everything -- human psychology to understand how people might feel…

Claude is perfectly capable of all of this. Give it access to meeting notes and notion/linear and it can elegantly connect the dots within the context of a given problem.

Re: Greg Knauss Is Losing Himself

#54

Post by bigbadfeline »

zaphar wrote: post #36
butILoveLife wrote: post #23

Earlier quoted context omitted.

This might have been true pre-agent AI programming, but honestly the code seems better than ever. It finds edge cases better than me. I know... I know buddy. The world changed and I don't know if I'm going to have a job.

I'm every bit as immersed in this as you are. I've been developing my own custom claude code plugins that allow me to delegate more and more the agents. But the one thing the agent is not reliably doing for me is making sound architectural choices and maintaining long term business context and how it intersects with those architectural choices. I tried teaching all of that in system prompts and documentation and it b…

I'd try a different approach - mechanical engineering isn't that hard and it can benefit greatly from developing some specialized agents and fine-tuned LLMs for it. As a side benefit, that approach happens to create some software jobs too, open source for best results.

Re: Greg Knauss Is Losing Himself

#55

Post by Throaway1985123 »

bee_rider wrote: post #7
gtowey wrote: post #5

LLMs can't be strategic because they do not understand the big picture -- that the real work of good software is balancing a hundred different constraints in a way that produces the optimal result for the humans who use it. It's not all that different from the state of big corp software today! Large organizations with layers of management tend to lose all abiliy to keep a consistent strategy. They tend to go all in o…

Why can’t LLMs understand the big picture? I mean, a lot of companies have most of their information available in a digital form at this point, so it could be consumed by the LLM. I think if anything, we have a better chance in the little picture: you can go to lunch with your engineering coworkers or talk to somebody on the factory floor and get insights that will never touch the computers. Giant systems of constrai…

They just can't yet. They'll tell you themselves they can only take in a certain amount of a context window.

Re: Greg Knauss Is Losing Himself

#56

Post by Throaway1985123 »

braebo wrote: post #53
gtowey wrote: post #21

Earlier quoted context omitted.

I would say that it's very germane to my original statement. Understanding is absolutely fundamental to strategy and it is pretty much why I can say LLMs can't be strategic. To really strategize you have to have mental model of well, everything and be able to sift through that model to know what elements are critical or not. And it includes absolutely everything -- human psychology to understand how people might feel…

Claude is perfectly capable of all of this. Give it access to meeting notes and notion/linear and it can elegantly connect the dots within the context of a given problem.

yes, its just a matter of capability, not skill

Re: Greg Knauss Is Losing Himself

#57

Post by Throaway1985123 »

sp1nningaway wrote: post #39
gtowey wrote: post #5

LLMs can't be strategic because they do not understand the big picture -- that the real work of good software is balancing a hundred different constraints in a way that produces the optimal result for the humans who use it. It's not all that different from the state of big corp software today! Large organizations with layers of management tend to lose all abiliy to keep a consistent strategy. They tend to go all in o…

Yes! "Does an AI know how to do that? Does a coding assistant know that an app is really a giant collection of details?" There are just so many small decisions that add up to a consistent vision for a piece of software. It doesn't seem like LLMs are going to be able to meaningfully contribute to that in the near future. I tried vibecoding my own workout tracker, but there were so many small details to think through t…

Right, it's people who can't code (and cant afford to hire a coder) that can use LLM's to replace coders, but oyu still need to sit through it and iterate. More so than with a human being, because of the dumb mistakes LLMs still make, so you need a patient and consistent vision.

Re: Greg Knauss Is Losing Himself

#58

Post by troupo »

braebo wrote: post #53
gtowey wrote: post #21

Earlier quoted context omitted.

I would say that it's very germane to my original statement. Understanding is absolutely fundamental to strategy and it is pretty much why I can say LLMs can't be strategic. To really strategize you have to have mental model of well, everything and be able to sift through that model to know what elements are critical or not. And it includes absolutely everything -- human psychology to understand how people might feel…

Claude is perfectly capable of all of this. Give it access to meeting notes and notion/linear and it can elegantly connect the dots within the context of a given problem.

It routinely can't "connect dots" on a 10 kloc project with design notes right there in the same project.

It routinely cannot read files more than 2k lines long.

You can't even provide detailed CLAUDE.md instructions because "file is too large and will affect context".

But sure. "Just give it access to a magnitude more info and it will be able to do stuff".

Re: Greg Knauss Is Losing Himself

#59

Post by switchbak »

aspenmartin wrote: post #37
switchbak wrote: post #34

Earlier quoted context omitted.

"Im not even sure we will need maintain software" (sic) - I'm not sure what your specific background is, but with a statement like that you lose all legitimacy to me.

Writings on the wall, it is true, tech debt will no longer be a thing to care about. "but who will maintain it?" massive massive question, rapidly becoming completely irrelevant "but who will review it?" humans sure, with the assistance of ai, writing is also on the wall: AI will soon become more adept at code review than any human I can understand "losing all legitimacy" being a thing, but to me that is an obvious k…

Trust me, I’m a well seasoned leathery developer and I’m no newbie when it comes to using AI. But this level of irrational exuberance is so over the top I just can’t take it seriously.

Yes, in the very long term I expect this to be able to replace large swaths of the sw dev lifecycle, product, ideation, the whole kaboodle. That’s a long way off, whatever “a long way off” means in this accelerated timeline.

For the next bunch of years, yes you’ll have to worry about architecture, coupling, testing, etc. I’m happy to have my competitors share your attitude, cause we’ll smoke them in the market.

Re: Greg Knauss Is Losing Himself

#60

Post by manxiemanx »

bee_rider wrote: post #7
gtowey wrote: post #5

LLMs can't be strategic because they do not understand the big picture -- that the real work of good software is balancing a hundred different constraints in a way that produces the optimal result for the humans who use it. It's not all that different from the state of big corp software today! Large organizations with layers of management tend to lose all abiliy to keep a consistent strategy. They tend to go all in o…

Why can’t LLMs understand the big picture? I mean, a lot of companies have most of their information available in a digital form at this point, so it could be consumed by the LLM. I think if anything, we have a better chance in the little picture: you can go to lunch with your engineering coworkers or talk to somebody on the factory floor and get insights that will never touch the computers. Giant systems of constrai…

You don’t understand how LLMs work. An LLM can’t understand the big picture because it doesn’t understand. Period. It works more like an autocorrect
Post reply on HN