It seems that people are using LLMs to generate code but many complain of sub par code. I recall the early days of virtualization when folks will use it but complain about performance. HW capacity continued to improve until virtualization became de facto standard. I wonder if sub par code will become better as more powerful agents models or compute become available.
While most folks are quick to write off agentic trading attempts for various reasons, one strength that I see in using LLMs is its capability to bring together disparate information sources and chart a path forward.I do agree it is a very advanced word calculator but that seems to work most of the time unless there is a massive information gap in the original data sources.
Wouldn’t we have more restaurants if there was no microwave ovens? But microwave oven also gave rise to many frozen food industry. Overall more industrializations.
