AI

Stephanie2: An AI that texts with human-like timing

Kari Jaaskelainen

12 Jan 2026 — 1 min read

Texting with AI can feel off—messages arrive in odd bursts with no real “thinking” pauses. Stephanie2 changes that.

Decides to send or wait: At every step, it chooses to message now or hold, like a human pausing to think.
Natural timing: It models delay as thinking time + typing time, adapting pace to the conversation.
Better evaluation: A time-window dual-agent setup generates realistic chat histories for human and automatic tests.

Results: Stephanie2 outperforms Stephanie1 on naturalness and engagement, and more often passes a role-identification Turing test—people have a harder time telling it’s an AI.

Why it matters: more lifelike pacing can make customer support, social companions, tutoring, and team chat feel smoother and more trustworthy.

Paper: https://arxiv.org/abs/2601.05657

Paper: https://arxiv.org/abs/2601.05657v1

Register: https://www.AiFeta.com

AI Chatbots ConversationalAI HCI NLP UX Research ArXiv

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added