cd /news/large-language-models/ai-allegory-steganography-in-claude-… · home › topics › large-language-models › article
[ARTICLE · art-45797] src=lesswrong.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

'AI allegory steganography' in Claude short stories in the Unslop contest?

Gwern reports that Claude-generated short stories in the Unslop contest may contain AI allegory steganography, suggesting hidden messages about AI within the narratives.

read1 min views44 publishedJul 1, 2026
'AI allegory steganography' in Claude short stories in the Unslop contest?
Image: Lesswrong (auto-discovered)

x This website requires javascript to properly function. Consider activating javascript to get access to all site functionality. LESSWRONG LW Login 'AI allegory steganography' in Claude short stories in the Unslop contest? — LessWrong Personal Blog 18 'AI allegory steganography' in Claude short stories in the Unslop contest? by gwern 1st Jul 2026 1 min read 0 18 This is a linkpost for https://www.hyperstitionai.com/unslop-results 0 Comments 0 New Comment Submit Moderation Log More from gwern View more Curated and popular this week

source & further reading
lesswrong.com — original article METR Researcher Thomas Kwa Hired by OpenAI Q2.5 2026 Timelines Update: Uplift and Revenue Case for Funding AI Safety in Japan
── more in #large-language-models 4 stories · sorted by recency
── more on @claude 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ai-allegory-steganog…] indexed:0 read:1min 2026-07-01 · —