When you zoom out on the time scale it makes more sense. I think he's got a point. Both CLIs and GUIs are "command based". LLM prompts are more declarative. You describe what you want.
Well LLMs are also “command-based”. They are called prompts. In fact they’d just continue the text but were specifically trained by RLHF to be command-following.
Actually, we can make automomous agents and agentic behavior without LLMs very well, for decades. And we can program them with declarative instructions much more precisely than with natural language.
The thing LLMs seem to do is just give non-experts a lot of the tools to get some basic things done that only experts could do for now. This has to do with the LLM modeling the domain space and reading what experts have said thus far, and allowing a non-expert to kind of handwave and produce results.
You’re still in the command paradigm with some batch processing thrown in. With an LLM interface to a db you don’t write queries, you express an intent such as “I’d like to know why my customers are not resubscribing” and the LLM will write one or more queries and then interpret the results to give you an answer in plain English with a chart attached.
Actually, we can make automomous agents and agentic behavior without LLMs very well, for decades. And we can program them with declarative instructions much more precisely than with natural language.
The thing LLMs seem to do is just give non-experts a lot of the tools to get some basic things done that only experts could do for now. This has to do with the LLM modeling the domain space and reading what experts have said thus far, and allowing a non-expert to kind of handwave and produce results.