> dismissing the possibilites of agentic coding as inherently non-SWE is rather short-sighted
The author does not. I recommend reading the whole article, IMO it shows rare (but growing) maturity about software development during this current age of AI tools (I mean in terms of practical day to day use, eg. ignoring (like everybody in tech) the environmental costs). But you might have been misled by how many people have adopted “vibe coding” to mean any use of ai in software dev.
From the article:
> A vibe coder gives the model a goal, but a software engineer gives the model a bounded task. The bounded task is where the engineering happens. Use this interface. Do not touch this layer. And so on. A good prompt is not magic here. It is usually evidence that the engineer already understands the boundary.
You actually proved it’s a story: for some people it’s news that couples can live in different houses and have any other type of romantic relationship than dating.
In your experience what’s the most convenient e-ink device for free ebooks? Ie Kindle is optimized for amazon so probably not the most convenient for this.
Interesting, best of luck! What are your closest competitors? And do you intend to provide other tiers for above 39, or are “digital nomads” above that age too few?
The question here may not be face to face vs remotely, but a person vs a rudimentary AI. Can one feel acceptance and support from a chatbot that has no sense of self?
They survived the Judith Miller controversy. What is it about the HRC-NYT emails that ends their credibility in ways that Judith Miller didn't?
edit: I can't think of a good reason to downvote this question (please do explain), but I'll rephrase: the Judith Miller Iraq reporting was bad to say the least, and they got rid of her. In this case I am under the impression that the problem is a few isolated cases, but I'm not well educated and am possibly missing something. What about these emails makes this a sweeping issue over the whole organization, as opposed to a few reporters having abused their welcome?
The author does not. I recommend reading the whole article, IMO it shows rare (but growing) maturity about software development during this current age of AI tools (I mean in terms of practical day to day use, eg. ignoring (like everybody in tech) the environmental costs). But you might have been misled by how many people have adopted “vibe coding” to mean any use of ai in software dev.
From the article:
> A vibe coder gives the model a goal, but a software engineer gives the model a bounded task. The bounded task is where the engineering happens. Use this interface. Do not touch this layer. And so on. A good prompt is not magic here. It is usually evidence that the engineer already understands the boundary.