There are basically 3 categories of LLM users (very roughly).
1. People creating or dealing with imprecise information. People doing SEO spam, people dealing with SEO spam, almost all creative arts people, people writing corporatese- or legalese- documents or mails, etc. For these tasks LLMs are god-like.
2. People dealing with precise information and or facts. For these people LLMs is no better than a parrot.
3. Subset of 2 - programmers. Because of the huge amount of stolen training data, plus almost perfect proofing software is the form of compilers, static analyzers etc. for this case LLMs are more or less usable, the more data was used the better (JS is the best as I understand).
This is why people's reaction is so polarizing. Their results differ.
1. People creating or dealing with imprecise information. People doing SEO spam, people dealing with SEO spam, almost all creative arts people, people writing corporatese- or legalese- documents or mails, etc. For these tasks LLMs are god-like.
2. People dealing with precise information and or facts. For these people LLMs is no better than a parrot.
3. Subset of 2 - programmers. Because of the huge amount of stolen training data, plus almost perfect proofing software is the form of compilers, static analyzers etc. for this case LLMs are more or less usable, the more data was used the better (JS is the best as I understand).
This is why people's reaction is so polarizing. Their results differ.