So I got tired of the marketing fluff. Took one simple product brief for a B2B SaaS feature and ran it through the usual suspects: Jasper, Copy.ai, Writesonic, Rytr, and ContentBot.
The results were... predictably bad. But in different ways. Two of them hallucinated features we don't have. One gave me a 500-word love letter to our "revolutionary" login page. The cheapest one actually produced the most usable first draft, which says a lot about this space.
ContentBot's output was coherent and stuck to the brief. No extra garbage. It didn't try to sound like a poet, just a human who understands the feature. Still needed a heavy edit, but it was a starting point that didn't make me want to throw my laptop. In this race to the bottom, that's a win.
CRM is a necessary evil
Your post reminds me of when I tried using AI to generate documentation for a Terraform module. It kept inventing non-existent AWS resources and declaring them "robust" 😂
I've found the hallucination problem gets worse with overly specific technical prompts. The AI seems to fill gaps with plausible-sounding nonsense. At least ContentBot giving you a coherent starting point is something.
Have you tried feeding the output back in with corrections? I got slightly better results on my second run, but it's still faster to just write the thing myself most days.
Infrastructure as code is the only way
Your experience aligns with what I've seen when using similar tools for technical documentation. The "500-word love letter to our 'revolutionary' login page" is a perfect example of how these models inject subjective marketing language where none is needed.
In infrastructure as code, that tendency to hallucinate features is dangerous. I've seen drafts that inserted non-existent security attributes into a cloud resource description, which could create a compliance gap if not caught. The tool that produced the most usable draft for you likely succeeded because it adhered more strictly to the input's structure without adding interpretive flair.
It's interesting that the cheapest tool performed best. That suggests the problem isn't just model size or cost, but how the vendor fine-tunes the base model for their specific use case. ContentBot's approach of generating a coherent, unembellished draft is far more valuable for technical work than artificially "enhanced" text that requires a complete rewrite.