If all I have todo is ask the thing what I want, where is all the great new software? Why isn't everyone running fully bespoke operating systems by now?
While I agree with the sentiment that we shouldn't make things more complicated by inventing fancy names, we also shouldn't pretend that software engineering has become super simple now. Building a great piece of software remains super hard to do and finding better techniques for it affords real study.
Your post is annoying me quite a bit because it's super unfair to the linked post. Simon Willison isn't trying to coin a new term, he's just trying to start a collection of useful patterns. "Agentic engineering" is just the obvious term for software engineering using agents. What would you call it, "just asking things"?
> If all I have todo is ask the thing what I want, where is all the great new software? Why isn't everyone running fully bespoke operating systems by now?
I was speaking from a software engineer's point of view, in the context of the article, where one of the "agentic" patterns is ... test-driven development? Which you summon out of the agent by saying ... "Do test-driven development", more or less?
> What would you call it, "just asking things"?
I'd call it software engineering. What makes good software didn't suddenly change, and there's fundamentally no secret sauce to getting an agent to do it. If I think a class does too many things, then I tell the agent "This class does too many things, move X and Y methods into a new class".
I recently used it to watch "Revolution of our times", a documentary about the 2019 Hong Kong protests. As far as I could tell, this is the only legal way to stream the movie.
The television, the atom bomb, the cigarette rolling machine, and penicillin are also "just tools". They nevertheless changed our world entirely, for better or worse. If you ascribe the impact of AI to the people using AI, you will be utterly, completely bewildered by what is happening and what is going to happen.
It irritates me a bit that many comments on HN are like a Yelp review of the linked article instead of adding to the discussion of their comments. Maybe you see HN primarily as a community-curated list of links while I see it as a place of discussions?
In this thread, for example, wccrawford gave an interesting perspective on choices in life. While they used the linked article as a reference point, the contents of their comment stand entirely on their own. The information value in the linked article is not that important, the value of the discussion is much more important. To me, that is.
But there are other platforms out there (especially for books) that people will prefer if they make it easier to find high-quality content. I’m with the poster you replied to; it would make sense for Amazon to go after these fake products.
It's a particularly bad problem for books, but it's a problem for every product category. Unless Amazon sees people abandoning them in large numbers (personally, I haven't ordered from them in years) they're not going to change.
Murakami wrote a non-fiction book about the Sarin attacks and the Aum cult, Underworld.
I’m not sure if it’s accurate (he’s a fiction writer, afterall) but it’s very fascinating and sent many chills down my spine.
No different than other cults. A bunch of once aimless people who found purpose by subsuming their existences to the will of a venerated man (who teaches yoga in his apartment.)
> The confusion here comes from our misunderstanding of mathematics. Much of the math that mechanical engineers use is continuous math. This is where we work over a continuous domain, like real numbers. Things like calculus, trigonometry, and differential equations are in this category. This is what most people in the US learn in high school, codifying it as what they think of as “math”.
> In software, we don’t use these things, leading to the conception that we don’t use math. But we actually use discrete math, where we deal exclusively with non-continuous numbers. This includes things like graph theory, logic, and combinatorics. You might not realize that you are using these, but you do. They’re just so internalized in software that we don’t see them as math! In fact most of computer science is viewable as a branch of mathematics. Every time you simplify a conditional or work through the performance complexity of an algorithm, you are using math. Just because there are no integrals doesn’t mean we are mathless.
I'd be interested to hear more about this. What actually defines "math" then?
I've heard computer science described as "applied mathematics". And if mathematics is a branch of philosophy, then perhaps software engineering is a distant branch (or the most cutting-edge frontier) of "applied philosophy".
While I agree with the sentiment that we shouldn't make things more complicated by inventing fancy names, we also shouldn't pretend that software engineering has become super simple now. Building a great piece of software remains super hard to do and finding better techniques for it affords real study.
Your post is annoying me quite a bit because it's super unfair to the linked post. Simon Willison isn't trying to coin a new term, he's just trying to start a collection of useful patterns. "Agentic engineering" is just the obvious term for software engineering using agents. What would you call it, "just asking things"?
reply