Rendered at 11:37:59 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Nevermark 7 hours ago [-]
I had to ask Fable to create a skill for using proper fourth grade writing when fourth grade writing is enough, use the canonical terms for things, and reference things directly, not with creative indirections.
It is as if Fable skipped any basic writing class, but went straight to poetry, advertising-copy and CEO-speak classes and somehow combined them.
After half a day of giving feedback, instead of work, the skill finally clicked.
Now Fable reviews and rewrites every single one of its own responses, without me ever having to ask. On my dime.
I found the most efficient feedback was being ruthless on the simplest shortest sentences which had any over complication or ambiguity. And occasionally, giving it back a rewrite of one of those long running sentences that is mulch the whole way.
Then tell it to update its skill, and rewrite. Over and over.
It has been a profound relief.
If I ever read "the X's own Y" again, or a five word sentence that somehow needs to be structured as "First second: third fourth fifth.", I don't know what I might do. Just give me some aspirin and m-dashes, straight up —— please!
rochansinha 3 hours ago [-]
went through the whole phase of
asd-ste100 -> caveman -> wait-what -> “remove mannered prose”
And a few others..
Now I just use a vale lint script I made using what worked from the skills and lint the output (docs and scripts) and just ask it to write in plain technical English for its chat messages with full context.
Skills just make the entire process bloated beyond belief (apart from the needless context rot and token usage)
goodusername 14 hours ago [-]
Seems promising, will have to try it out. It really is grating to read output from opus 5 currently. Never heard of the term "mannered prose" before.
I'm constantly debating with myself whether to add more to my claude.md, or whether to simplify it before adding new stuff.
mdritch 9 hours ago [-]
Glad you got something out of it! Yes, it's hard to tell when something should be in claude.md or added to each subsequent prompt in a session. I need to do a similar analysis here for multi-turn settings and especially coding settings.
It is as if Fable skipped any basic writing class, but went straight to poetry, advertising-copy and CEO-speak classes and somehow combined them.
After half a day of giving feedback, instead of work, the skill finally clicked.
Now Fable reviews and rewrites every single one of its own responses, without me ever having to ask. On my dime.
I found the most efficient feedback was being ruthless on the simplest shortest sentences which had any over complication or ambiguity. And occasionally, giving it back a rewrite of one of those long running sentences that is mulch the whole way.
Then tell it to update its skill, and rewrite. Over and over.
It has been a profound relief.
If I ever read "the X's own Y" again, or a five word sentence that somehow needs to be structured as "First second: third fourth fifth.", I don't know what I might do. Just give me some aspirin and m-dashes, straight up —— please!