Text as a Universal Interface for Transferable Personalization

Kari Jaaskelainen

10 Jan 2026 — 1 min read

Personalized AI you can read, edit, and take anywhere

Most AI systems hide your preferences in opaque vectors. This work makes them plain English instead. Your "profile" becomes a short text summary the model can use across apps and tasks.

Interpretable: you can see and revise what the AI thinks you like.
Transferable: the same text works across models, tasks, and formats.
Adaptive: it evolves as you interact.

The team trains these text profiles in two stages: supervised learning on high-quality synthetic examples, then reinforcement learning to boost long-term usefulness and cross-task transfer.

Their 8B model, AlignXplore+, writes these summaries and achieved state-of-the-art results on nine benchmarks—outperforming much larger open-source models while generalizing across model families.

Paper: https://arxiv.org/abs/2601.04963v1

Paper: https://arxiv.org/abs/2601.04963v1

Register: https://www.AiFeta.com

ai personalization llm nlp machinelearning explainableai transferlearning reinforcementlearning

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

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 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

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

Personalized AI you can read, edit, and take anywhere

Read more

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

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

AI that explains itself—by following the science

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