Meet DeepPersona: AI personas that actually feel human

Kari Jaaskelainen

11 Nov 2025 — 1 min read

AI personas that actually feel human

What if our "AI citizens" behaved less like cardboard cutouts and more like real, diverse people? DeepPersona is a generative engine that builds rich, fully narrated synthetic personas at scale.

It first assembles a large, hierarchical taxonomy of human attributes by mining thousands of ChatGPT conversations. Then it progressively samples and weaves these attributes into coherent life stories—hundreds of structured traits and about 1 MB of narrative per persona, two orders deeper than prior work.

+32% attribute diversity
+44% profile uniqueness
+11.6% better personalized Q&A (GPT-4.1-mini, 10 metrics)
31.7% closer to human answers in social surveys
17% smaller gap on Big Five personality test

Why it matters: DeepPersona offers a scalable, privacy-free way to study behavior, personalize AI, and stress-test systems—without relying on real user profiles.

Paper: http://arxiv.org/abs/2511.07338v1

Paper: http://arxiv.org/abs/2511.07338v1

Register: https://www.AiFeta.com

AI LLM SyntheticPersonas AgentSimulation Personalization AIAlignment GenerativeAI NLP Research

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

AI personas that actually feel human

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)