Observation: Opus 4.7 (via chat) is near-useless for helping me iterate on google docs. For one, its reading comprehension seems very poor.
This is surprising because others say that the models give them tons of uplift. (And the main METR graph is just coding but still. And Opus 4.6 beat all humans on the GovAI work test. And the vibes!)
Hypotheses (not exclusive or exhaustive):
Claude Code and Cowork are much better, even for tasks like "iterate on a google doc"
Other models are much better for work like mine
I'm prompting the model terribly (or it's better at reading different file formats or something)
Other people are wrong, at least for work like mine; the models fool them with stuff that's subtly slop
(I am unusually good at noticing when suggestions are garbage)
Other people do legitimately get uplift, but I'm different in ways that make me not
Actually I incorrectly perceived the vibes; most people don't think they can get substantial uplift on tasks like mine
Anyway, the obvious things to do are:
Find someone who does work like mine and claims to get lots of uplift, and watch them use the AIs. Or get them to walk me through how to use the models to iterate on a google doc.
Check for blogposts about getting use out of AIs on tasks like mine.
I can see cleaning up formatting not being a timewarping black hole any more, but ... was Cmd/Ctrl+X, click, Ctrl+V, Ctrl+Z, correct click, Ctrl+V, Ctrl+Z, Ctrl+Z, correct selection, Ctrl+X, correct position (final v2) click, Ctrl+V really that slow in the old world? can you really ask claude to do that in less than the 10 seconds it took before? (and did you actually time it or just vibe time it?)
Fwiw, if a direction is simply describable, I do think I’m faster to tell Claude Code to do it (via Wispr Flow) than to mechanically do it. I also feel like there are some nice batching properties of relaying to it all-at-once the changes I want, without having to switch myself from conceptual thinking to mechanical operation and then back again, but I’m less sure of that
The thing that Claude helps with is telling me what things I might have broken when I did that ("Now that you moved this section in front of the other section, you introduce this concept after you have first used it, so you need to address that" or "you previously expanded the first use of an acronym, but that first use has changed" or "later on in this doc you refer to 'the first section' but that's no longer accurate").