Worse, I am repeatedly being accused nowadays of being an LLM. It probably doesn’t help that I riff-write with only a rough outline of what I want to say, not how to say it.
If the accusation is that I am an inference engine pumping out words based on a trailing context window then I am guilty as charged. It’s just that I run on Fe + C6H12O6 + O2 (a bloodstream charged with lunch and air) instead of y/C/N2 -> Si+e- (sunlight, coal, and wind turned into silicon electrons.)
> If the accusation is that I am an inference engine pumping out words based on a trailing context window then I am guilty as charged. It’s just that I run on Fe + C6H12O6 + O2 (a bloodstream charged with lunch and air) instead of y/C/N2 -> Si+e- (sunlight, coal, and wind turned into silicon electrons.)
This sort of tells me that you are pro-LLM, and most pro-LLM people mostly paste the contents of their ChatGPT output and try to pass it off as their own.
Given that you say you aren't, the most likely explanation might be that you are spending a lot of time reading LLM prose, and are starting to write like it now too.
I got a pretty interesting ai detection demo run through historic HN data, would love to see if HN could make use of this tech for HN. But i have no clue how to reach out or who might be a contact here.
Make it into a browser extension. Or, honestly, just a page with outputs and a tip jar. If there are interesting findings, highlight them-maybe blog about it and post that.
If the accusation is that I am an inference engine pumping out words based on a trailing context window then I am guilty as charged. It’s just that I run on Fe + C6H12O6 + O2 (a bloodstream charged with lunch and air) instead of y/C/N2 -> Si+e- (sunlight, coal, and wind turned into silicon electrons.)