I didn't notice either. Maybe he provides a good starting point so that the result doesn't look like an LLM. He also says it's target time for writing a post is 30 minutes. I spend several cumulated hours on my side!
The article doesn’t say it was written by AI. It says the opposite.
I've been trying to write posts more quickly because, with LLMs, it's so much easier to look at data and figure things out but, since I'm not writingn with LLMs, the time it takes to write something up hasn't fundamentally changed […]
The postscript implies that the author uses LLMs to try to derive insights from their experimental data. And footnote two implies that this post is not one of those “experimental/data posts”. Even for those other experimental posts, the postscript says that the author writes up the posts himself – it’s just the analysis that is AI-assisted.
vamolessa | 13 hours ago
it's a cool post with cool examples and anecdotes! appreciated that
but it would be nice if the written by ai wasnt at the very bottom (my ai detection skills are rather poor)
vbernat | 12 hours ago
I didn't notice either. Maybe he provides a good starting point so that the result doesn't look like an LLM. He also says it's target time for writing a post is 30 minutes. I spend several cumulated hours on my side!
roryokane | 11 hours ago
The article doesn’t say it was written by AI. It says the opposite.
The postscript implies that the author uses LLMs to try to derive insights from their experimental data. And footnote two implies that this post is not one of those “experimental/data posts”. Even for those other experimental posts, the postscript says that the author writes up the posts himself – it’s just the analysis that is AI-assisted.