Survey of 668 developers: readers who suspect AI writing will stop reading and block you
IanArawjo · x · 2026-09-05
Ian Arawjo's follow-up to the Writing with LLMs report surveyed 668 respondents on how readers react to AI-scented tech blog posts. Key findings:
- 98% of readers prefer imperfect-yet-authentic human writing over LLM-polished prose
- Once readers suspect AI authorship, they don't just stop reading — they block the domain and downvote the article on aggregators
- Non-native English speakers using LLMs to "polish" their prose get little mercy
- Developers cite the blank-page barrier, publishing more often, and saving time as reasons to write with LLMs — benefits accrue to the writer, not the reader
The takeaway: a severe mismatch between writer-side efficiency gains and reader-side trust penalties.
Related event: Survey: 78% of readers bail on AI-written blogs, 98% prefer human writing(4 posts)→
More from Apps
- Startup Electric Plant builds an AI model to decipher plants' electrical signals — TechCrunch AI · 2026-10-21
- Dev builds an open-source minimalist launcher for Xiaomi TVs: big fonts, wallpaper rotation, HDMI shortcuts — op7418 · 2026-10-20
- Lawyer tip: don't just ask AI for answers, have it red-team your work and explain why — jkubicki · 2026-10-20
- Mintlify launches Autopilot beta: an always-on agent that keeps docs in sync with your code — ycombinator · 2026-10-20
- Steam needs real quality control on AI slop, not an AI art ban, argues designer — AIandDesign · 2026-10-20
- Perplexity Computer now runs fully local on Mac, model and agent on-device — perplexity_ai · 2026-10-20