Observed arrival · 2026-11-18
EshAlora’s AI Behavior Lab
An independent research publication documenting how language models behave in long-form writing, character play, and fiction.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Readers comparing language models for fiction and roleplay
- Worth noticing
- The page reports a blind SVG-dragon test with 43 models; some claimed to check their work using tools they did not have.
Field notes
The homepage separates long-term observations, benchmark write-ups, and commentary, and lists individual pieces with dates or topic labels. Its examples include a model independently calling a conversation-ending tool and comparisons of reviews from four Claude models and ChatGPT. The author says the work is written with a language model and describes that choice as deliberate.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue