Are Smarter AI Models Safer? It Depends

Kari Jaaskelainen

16 Jan 2026 — 1 min read

Are smarter AI models safer?

A new safety report puts seven frontier models—GPT-5.2, Gemini 3 Pro, Qwen3‑VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5—through a unified, cross‑modal test spanning language, vision‑language, and image generation.

Headline: Safety performance is highly uneven. GPT‑5.2 is the most balanced overall, but no model is safe across the board.
Benchmarks ≠ reality: All models drop sharply under adversarial prompts, in both text and vision‑language tasks.
Multilingual gaps: Alignment can falter outside English, exposing policy and compliance blind spots.
Images: Text‑to‑image systems show better alignment on regulated categories yet remain brittle to tricky or ambiguous requests.

Bottom line: Safety is multidimensional—shaped by modality, language, and test method. Standardized, cross‑modal evaluations are essential to gauge real‑world risk and guide responsible deployment.

Read the report: https://arxiv.org/abs/2601.10527v1

Paper: https://arxiv.org/abs/2601.10527v1

Register: https://www.AiFeta.com

#AI #AISafety #LLM #Multimodal #ResponsibleAI #Evaluation #AdversarialRobustness

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

Are smarter AI models safer?

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