> You keep using these words but it causes circular logic as those are all defined by the same entity that is acting unilaterally.

It's not, in Germany we have separation of powers.

> The action the government took was not a "good" action by any moral standard.

Morals aren't binary. Morals have context.

Bob will never figure out there is an error in his paper. If someone tells him, the LLM will have trouble to figure it out as well, remember the LLM inserted the error to make it "look right".

Your perspective is cut off. In the real world Bob is supposed to produce outcomes that work. If he moves on into the industry and keeps producing hallucinated, skewed, manipulated nonsense, then he will fall flat instantly. If he manages to survive unnoticed, he will become CEO. The latter rather unlikely.

This is my primary personal concern. I think it could be an silent psychological landmine going off way too late (sic).

In a living codebase you spent long stretches to learn how it works. It's like reading a book that doesn't match your taste, but you eventually need to understand and edit it, so you push through. That process is extremely valuable, you will get familiar with the codebase, you map it out in your head, you imagine big red alerts on the problematic stuff. Over time you become more and more efficient editing and refactoring the code.

The short term state of AI is pretty much outlined by you. You get a high level bug or task, you rephrase it into proper technical instructions and let a coding agent fill in the code. Yell a few times. Fix problems by hand.

But you are already "detached" from the codebase, you have to learn it the hard way. Each time your agent is too stupid. You are less efficient, at least in this phase. But your overall understanding of the codebase will degrade over time. Once the serious data corruption hits the company, it will take weeks to figure it out.

I think this psychological detachment can potentially play out really bad for the whole industry. If we get stuck for too long in this weird phase, the whole tech talent pool might implode. (Is anyone working on plumbing LLMs?)

I like it a lot, I find the chat driven workflow very tiring and a lot of information gets lost in translation until LLMs just refuse to be useful.

How does the human intervention work out? Do you use a mix of spec and audit editing to get into the ready to generate state? How high is the success/error rate if you generate from tasks to code, do LLMs forget/mess up things or does it feel better?

The spec driven approach is potentially better for writing things from scratch, do you have any plans for existing code?

The example is really lean and straightforward. I don't use coding agents, but this is some good overview and should help everyone to understand that coding agents may have sophisticated outcomes, but the raw interaction isn't magical at all.

It's also a good example that you can turn any useful code component that requires 1k LOC into a mess of 500k LOC.