1. Punch cards -> Assembly languages
2. Assembly languages -> Compiled languages
3. Compiled languages -> Interpreted languages
4. Interpreted languages -> Agentic LLM prompting
I've tried the latest and greatest agentic CLI and toolings with the public SOTA models.
I think this is a productivity jump equivalent to maybe punch cards -> compiled languages, and that's it. Something like a 40% increase, but nowhere close to exponential.
1. Punch cards -> Assembly languages
Here, for example, is the Punch Card for a single FORTRAN statement: https://en.wikipedia.org/wiki/File:FortranCardPROJ039.agr.jp...
PunchCards were an input technology, they were in no way limited to either assembley languages or to FORTRAN.
You might be thinking of programming in assembly via switch flipping or plug jacking.
I'm also reminding that we tried whole "make it look like human language" with COBOL and it turned out that language wasn't a bottleneck, the ability of people to specify exactly what they want was the bottleneck. Once you have exact spec, even writing code on your own isn't all that hard but extracting that from stakeolders have always been the harder part of the programming.
And compiled and interpreted languages evolved alongside each other in the 1950s-1970s.