Software development has always evolved. Sometimes slowly, sometimes quicker.
LLMs have brought a different unlock, and for everything we're seeing become easier, it allows people learn to use the tools to take on solving problems that couldn't be approached before.
The cost of code actually increased; code debt is being accumulated faster than we can clean it up.
Can a llm predict the price of a change to a codebase in tokens and predict the origin of the price, aka cam it see good and bad architecture?
Some code bases better than others but the top models can.
Ask it to do so, would love to know your results.
The worse problem is blog posts after the cost of writing collapsed.
Not everything has to be written as though it’s a middle manager’s idea of what makes for a good TED talk.
I closed the tab after seeing the AI hero image. Good to know I didn't miss anything.
I read this entire article and didn’t sniff AI, plus it had some good insights…?
[delayed]
Feels like a human-authored outline that was run through AI to make it into an article.
Well it contains a typo, so it made a cock up.
Software development has always evolved. Sometimes slowly, sometimes quicker.
LLMs have brought a different unlock, and for everything we're seeing become easier, it allows people learn to use the tools to take on solving problems that couldn't be approached before.