“ There were tasks I could have done in 20 minutes easily, that took 5 minutes of an AI agent, and then 2 days for me to review.”
This is using AI for productivity in any domain, in a nutshell. I just wrote a book using Claude as an experiment, and while the thing got done and it was an amazing tool and a great experience, what I’m left with is a book where every line needs rewriting, there are logical inconsistencies throughout, and the style is so bad it should actually just be binned rather than rewritten.
It’s not that it’s intractable, and I genuinely enjoyed the process working with Claude. But responding to the initial post – using Claude I managed to do three months work in about two weeks, but at the end of that I then realised I probably had three months of improvements and rewrites and corrections left to go if it was going to be to be a book worth anyone else reading.
So 3.5 months estimated total. That actually makes sense.
I think this is a common experience, no matter what field or era you're in. Once you start applying QA to some promising new process or technology for the first time, the whole cycle slows right down.
But that's actually the point where things get interesting, and innovators get to roll up their sleeves. I wouldn't give up!
Yeah it’s interesting, and if I was to do the work then it’s likely going to be a better book with Claude’s input. But at the same time if I’d have not bothered using Claude then I’d have the same three months work to do and wouldn’t have lost two weeks trying to do it using Claude. I had the Claude subscription for two months and I did make some really fun things during that time but right now it seems that even at the paltry sum of $20 a month I don’t even need it so cancelled.
This is also partly me as an investor too, seeing how much of the AI circular economy holds up. And I’m not sure it can hold up once Claude and ChatGPT have to start charging retail customers what it actually costs to run the service if they can’t bring down the cost of inference to be actually profitable at $20-30 a month.
gizajob · · focus · HN ↗
This is using AI for productivity in any domain, in a nutshell. I just wrote a book using Claude as an experiment, and while the thing got done and it was an amazing tool and a great experience, what I’m left with is a book where every line needs rewriting, there are logical inconsistencies throughout, and the style is so bad it should actually just be binned rather than rewritten.
Kim_Bruning · · focus · HN ↗
gizajob · · focus · HN ↗
Kim_Bruning · · focus · HN ↗
I think this is a common experience, no matter what field or era you're in. Once you start applying QA to some promising new process or technology for the first time, the whole cycle slows right down.
But that's actually the point where things get interesting, and innovators get to roll up their sleeves. I wouldn't give up!
gizajob · · focus · HN ↗
This is also partly me as an investor too, seeing how much of the AI circular economy holds up. And I’m not sure it can hold up once Claude and ChatGPT have to start charging retail customers what it actually costs to run the service if they can’t bring down the cost of inference to be actually profitable at $20-30 a month.