I understand model output put back into training would be an issue, but if model output is guided by multiple prompts and edited by the author to his/her liking wouldn't that at least be marginally useful?
You are ignoring the obvious difference between errors introduced while translating one near-formal-intent-clear language to another as opposed to ambiguous-natural-language to code done through a non-deterministic intermediary. At some point in the future the non-deterministic intermediary will become stable enough (when temperature is low and model versions won't affect output much) but the ambiguity of the prompting language is still going to remain an issue. Hence, read before commit will always be a requirement I think.
A good friend of mine wrote somewhere that at about 5 agents or so per project is when he is the bottleneck. I respect that assessment. Trust but verify. This way of getting faster output by removing that bottleneck altogether is, at least for me, not a good path forward.
This is pretty much how I use LLMs as well. These interactions have convinced me that while the LLMs are very convincing with persuasive arguments, they are wrong often on things I am good at; so much so that I would have a hard time opening PRs for code edited by them without reading it carefully. Gell-man amnesia and all that seems appropriate here even though that anthropomorphizes LLMs to an uncomfortable extent. At some point in the future I can see them becoming very good at recognizing my intent and also reasoning correctly. Not there yet.
I have nothing against automated code completion on steroids or agents. What I cannot condone is not reading and understanding the generated code. If you have not understood your agent generated code, you will be "surprised" for sure, sooner or later.
I don't know about you, but when the creator of a software says I have not read any of the code, I don't want to install or use it. Call me old fashioned. Really hoping this terrifying vibe coding future dies an early death before the incurred technical debt makes every digital interaction a landmine.
Also, if you do not want to spend on any specialized fountain pen flush solution, diluted windex works very well. From the smell I am willing to bet that most fountain pen cleaning solutions are exactly that.
I don't think in this use case that would be very logical. If we want to deploy survey telescopes and use SpaceX for it, what is the harm. Once deployed it is deployed. On the other hand if it was about deploying the nuclear deflection device through some SpaceX rocket I would be worried. I wouldn't be surprised if musk tried some destructive grand standing at the last moment derailing the whole thing and dooming us all.
Apparently as per the house majority leader's office they have no plans to vote on this now[1]. May be he was just making a factual statement on what they have on schedule. Cynic in me thinks it is just the usual dysfunction since the republicans were in favor of this in the Senate so the House doesn't want to do anything about it. Really how long does it take to vote on an almost non-event non divisive bill.
[1] https://www.npr.org/2022/03/15/1086773840/daylight-saving-ti...