A parallel question: do you think Python being so entrenched in LLMs model weights means that future new programming languages are just going to resemble Python? Corpus means models that write that language means more corpus of that language.
OH, but LLMs are even better at natural language than they are with Python (which is why you have to often go from PL code to NL to get it to do something well, then go back to PL from the updated NL). So any kind of new language they develop will definitely be some kind of natural language where they derive semantic meaning from it to quickly use some deterministic PL to do something.
I suspect it will not be a language in the traditional sense. Instead of describing how to build a system, it would describe the system's entities, relationships, goals, constraints, NFRs etc...
The application model becomes the source of truth, and the code will be the generated artifact. A single spec defined and code generated will be optimized for web, mobile, desktop, api, etc...
The spec itself can be in a yaml type format or a hierarchical knowledge graph...
A parallel question: do you think Python being so entrenched in LLMs model weights means that future new programming languages are just going to resemble Python? Corpus means models that write that language means more corpus of that language.
OH, but LLMs are even better at natural language than they are with Python (which is why you have to often go from PL code to NL to get it to do something well, then go back to PL from the updated NL). So any kind of new language they develop will definitely be some kind of natural language where they derive semantic meaning from it to quickly use some deterministic PL to do something.
I suspect it will not be a language in the traditional sense. Instead of describing how to build a system, it would describe the system's entities, relationships, goals, constraints, NFRs etc... The application model becomes the source of truth, and the code will be the generated artifact. A single spec defined and code generated will be optimized for web, mobile, desktop, api, etc...
The spec itself can be in a yaml type format or a hierarchical knowledge graph...
This reads exactly like 'model driven development' and 'language workbenches' hype from 20 years ago.
Uncanny. Jet Brains has had that on early access since 2005. Literally 20 years ago people were dreaming about this new abstraction thing.
Text source code is a low energy configuration for representing software. Using LLMs is a much higher energy state.
Interesting. I've never heard of this before https://en.wikipedia.org/wiki/Language_workbench
didn't know about these... I need to go read up on them now...
It will be unimaginably amazing!
0101001010100001
English with syntax for contextual awareness. Can be a in a structured format or schematic format JSON or MD