How to de-slop AI writing: score multiple generations against each other, skip SFT

ivan_bezdomny · x · 2026-08-25

ivanbezdomny shares hands-on lessons from building non-slop news writing: he narrows to one task, and since SFT doesn't really work, he scores multiple generations of the same news against each other. He also counts word/phrase frequencies from tweets to compare language distributions, admitting this resource is underused. General-purpose models do a poor job removing slop beyond banning certain vocabulary, he says; a longer post is coming.

Related event: Developer Shares Recipe for De-Slopping AI Writing: Multi-Version Self-Scoring(3 posts)→

Original post →

More from Research

Research channel →