AI

Turn the Memory Dial: Smarter Personalization for AI Assistants

Kari Jaaskelainen

10 Jan 2026 — 1 min read

AI assistants that remember our past chats can feel personalized, but there is a catch. Using all history can anchor them to old habits; using none makes them forget who you are.

SteeM (Steerable Memory Agent) introduces a simple idea: a controllable memory dial.

Fresh-start mode: prioritize new ideas and avoid being anchored by history.
High-fidelity mode: closely follow your past preferences and style.
A behavioral metric quantifies how much past interactions shape the current answer.

In tests across different tasks, SteeM outperformed standard prompting and rigid memory masking, offering finer, user-driven personalization.

Why it matters: better long-term collaboration, consistent tone when you want it, and freedom to reinvent when you do not.

Paper: https://arxiv.org/abs/2601.05107

Paper: https://arxiv.org/abs/2601.05107v1

Register: https://www.AiFeta.com

AI LLM personalization memory HCI NLP research

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