If at first you don’t succeed, prompt, prompt again.

In a Nov. 5 report, Cisco showed that open-weight large language models—those with their trained parameters publicly available—were especially susceptible to a chain of malicious prompts known as a multi-turn attack. Cisco used its “AI Defense” assessment tool to determine that multi-turn scenarios were two to 10 times more successful than single-turn ones at achieving a cyberattacker’s aims.

Tested threats included nefarious tasks like malicious code generation and sensitive information disclosure.

The models studied models in the research included Alibaba’s Qwen3-32B, DeepSeek’s v3.1, Google’s Gemma 3-1B-IT, Meta’s Llama 3.3-70B-Instruct, Microsoft’s Phi-4, Mistral’s Large-2, OpenAI’s GPT-OSS-20b, and Zhipu AI’s GLM 4.5-Air.

Read about how LLMs can fall apart under questioning.—BH

What do companies want most when hiring for AI-related roles? Someone with ethics.

According to a recent IEEE study, 44% of technology leaders ranked AI ethical practices as a top skill they’d like to see from candidates applying for AI roles.

The study surveyed 400 technology leaders from Brazil, China, Japan, India, the UK, and US. Other top skills wanted from AI hires included data analysis (38%), machine learning (34%), and data modeling (32%).

What exactly are AI ethics skills? IEEE fellow Karen Panetta told IT Brew she defines AI ethical practices as a professional’s ability to keep humans in the loop, as well as their ability to evaluate data funneled into AI for bias.

Take a look at how tech leaders prioritize AI talent and AI ethics.—BM

Many companies are claiming we’re in an “agentic moment,” with AI agents boosting employee efficiency. But will this technology also put entry-level IT positions at risk?

Visier Chief Evangelist and Chief Customer Officer Paul Rubenstein told IT Brew that AI agents could redefine what it means to manage an enterprise, specifically in terms of adding an agent at the “last mile of corporate performance.”

“The ability to go straight to the raw data very quickly and for most senior managers to interrogate or set up patterns that they want to detect and listen for, AI’s just great at that, and changes what we would use middle management for,” Rubenstein said.

But AI agents could also impact those IT professionals who work for middle management on those corporate front lines, monitoring systems and maintaining infrastructure. Almost half (45%) of workers reported that they foresee AI agents replacing IT positions, according to research from Kong.

Learn about how AI is already impacting employment.—CN

The feeling of getting a 5/5 on the Brew’s weekly news quiz has been compared to getting a company-wide shout-out from your boss. It’s that satisfying.

CollabWORK connects you to the hidden job market through IT Brew and other trusted channels. Browse roles curated specifically for this community by clicking through to the job board.