This is what struck me as well. I got weird undertones of 'Now you don't even need to have real memories! Just fabricate them.' They even prominently showcase edits of placing you with another person, further deepening disingenuous or parasocial relationships
>then tell it to give you the top 10 things wrong with the code, then tell it to fix the five of them that are valid and important.
I would be cautious of this. I've tried this multiple times and often it produces very subtle bugs. Sometimes the code is not bad enough to have 5 defects with it, but it will comply, and change things that don't need to. You will find out in prod at some point.
To be clear, I'm instructing it to generate a list of issues for me. I then decide if anything on that list is worth fixing (or is an issue at all, etc.)
Crappy spreadsheet is just the codification of business processes. Those are inherently messy and there's lots of assumptions, lots of edge cases. That's why spreadsheets tend towards crappy on a long enough timeline. It's a fundamentally messy problem.
Spreadsheets are an abstraction over a messy reality, lossy. They were already generalizing reality.
Now we generalize the generalization. It is this lossy reality that people are worried about with AI in HN.
It's hard to appreciate the difference in 'abundance mentality' between the median US and EU person. It always struck me as an interesting culture difference. While both EU and US grew in prosperity post WWII, I feel the US narrative was quite on another level.
Interesting thought. Do you have any anecdotes regarding it? Seems you're basing it off personal experience or something you've heard many times, curious to know what that is
Mostly from personal experience and interacting with a lot of them, who form their little boy's clubs. It's especially bad in German Europe and Italy where the vast majority of leadership of extremely technical companies are largely business or law graduates.
I've been personally surprised that this doesn't come up more often. Most mature codebases span a decade or more, and especially in the web, there's so many layers of evolving technologies that were introduced during this time, resulting in complex geological layers forming in the codebase as the patterns evolved. That is not only a lot of lines of code, but a lot of nuance as well. Even a basic problem like routing can make these AIs fall flat on their face because of the sheer context and complexities involved
Hm. The 'prompt obedience' was definitely a huge step up, but there's a huge number of acceptable results to an image generation prompt, while for coding usually there a handful, many times just one right solution. So I don't think this parallel here is telling