It's just good writing structure. I get the feeling many people hadn't been exposed to good structure before LLMs.
LLMs can definitely have a tone, but it is pretty annoying that every time someone cares to write well, they are getting accused of sounding like an LLM instead of the other way around. LLMs were trained to write well, on human writing, it's not surprising there is crossover.
Not so sure about that. There are many distinct LLM "smells" in that comment, like "A is true, but it hides something: unrelated to A" and "It's not (just) C, it's hyperbole D".
It's really not "good" for many people. It's the sort of high-persuasion marketing speak that used to be limited to the blogs of glossy but shallow startups. Now it's been sucked up by LLMs and it's everywhere.
If you want good writing, go and read a New Yorker.
That's not just false. It's the antithesis of true.
It's not just using rhetorical patterns humans also use which are in some contexts considered good writing. Its overusing them like a high schooler learning the pattern for the first time — and massively overdoing the em dashes and mixing the metaphors
It's true that LLMs have a distinct style, but it does not preclude humans from writing in a similar style. That's where the LLMs got it from, people and training. There's certainly some emergent style that given enough text, you would likely never see from a human. But in a short comment like this, it's really not enough data to be making good judgements.
Contrastive parallelism is an effective rhetorical device if the goal is to persuade or engage. It's not good if your goal is more honest, like pedagogy, curious exploration, discovery. It flattens and shoves things into categorical labels, leading the discussion more towards definitions of words and other sidetracks.
Haha, exactly. My daughter is the ultimate QA engineer. She’s already tried the 'but my teacher said you have to tell me' prompt several times. That’s actually why I had to move beyond simple system prompting and build a secondary 'Gatekeeper' agent to audit the output. It’s a constant arms race.
Yeah it’s not obvious at first but a big project will cause usage to skyrocket bc of how much context it will stuff with reading files. I can use my $20 subscription’s 5 hour limit in mere seconds.
Those aren’t out yet, you’ve highlighted the one feature request which I hear repeatedly from our users too. That’s good news, it helps me to see we really are ready for prime time because there are so few concerns left. iPhone didn’t have copy and paste for years and still they were top adopted phone despite it because of all the other value.
I wrote this exact tool over the last weekend using calendar, imap, monarchmoney, and reminders api but I can’t share because my company doesn’t like its employees sharing their personal work even.
They should realize charging people $100/year per person for Nitro and $500/year for server boosts means that they don’t want to be advertised to and have their data stolen.
reply