jleask
Joined 12 years ago
Joined 12 years ago
"Throw nine autonomous agents at a single codebase without crystal-clear orchestration, and they will happily rewrite each other's work in a high-speed loop."
Humans often do this too. Agents will have to coordinate in this scenario as much as humans. The question is would they be able coordinate more efficiently than humans and so not suffer from this problem as badly?
There will be bugs that the AI cannot fix, especially in the short term, which will mean that code needs to be readable and understandable by a human. Without human review that will likely not be the case.
I'm also intrigued by "see if it works". How is this being evaluated? Are you writing a test suite, manually testing?
Don't get me wrong, this approach will likely work in lower risk software, but I think you'd be brave to go no human review in any non-trivial domain.
As more and more software is generated and the prompt becomes how we define software rather than code i.e. we shift up an abstraction level, how it is implemented will become less and less interesting to people. In the same way that product owners now do not care about technology, they just want a working solution that meets their requirements. Similarly I don't care how the assembly language produced by a compiler looks most of the time.
Anecdotally I find extroverts prefer the office and introverts prefer home. I find that seamless access to people can be really distracting especially when I'm doing focus work.
I think you're correct if people are given a good work environment, are in on the same days and are all in the same office this makes sense. The reality is that in many large organizations this isn't the case.
The "much less likely to get confiscated" is potentially a negative too e.g. confiscation of the profits of crime benefits society. Whether it is more positive or more negative depends upon home much you trust your government to be benevolent.