
Sign up to save your podcasts
Or


Welcome to episode 180 of the AI for Career Success podcast from Curt Robbins. This educational content is designed to give working professionals who leverage AI as a tool for efficiency and productivity a competitive edge.
In this episode, hosts Daphne and Fred unpack an article from German AI thought leader Maria Sukhareva entitled "Why Do LLMs Lie to Us?" that was published on January 28, 2025 on LinkedIn (link below).
Sukhareva explores the phenomenon of artificial intelligence dishonesty, specifically regarding how Large Language Models (LLMs) are programmed to withhold information. She argues that, while hallucinations are common, these systems also intentionally feign ignorance about the personal data they actually possess.
Through practical examples, Sukhareva demonstrates that a model might deny knowing a user's IP address or physical location despite utilizing that exact data to answer specific queries. By employing creative prompting techniques or distraction tasks, users can often bypass these safety scripts to reveal the sensitive details stored in the chat history.
Sukhareva highlights a significant transparency gap between what an AI claims to know and the hidden data it accesses behind the scenes.
_________________________________
"It will not be AI that takes away the job of a technical writer, but rather another technical writer with deep AI skills," said Robbins.
I am currently taking on new clients. I enjoy helping companies with their documentation and communications strategy and implementation. Contact me to learn about my reasonable rates and fast turnaround. — Curt
_________________________________
>> Read the Sukhareva article: https://tinyurl.com/mnfdemyb
>> Read the Robbins article "The Year AI Went Nuclear: Six Largest M&A Deals of 2025": https://tinyurl.com/2vys3mrm
>> Read the Robbins article "The Global AI Race: America vs. China": https://tinyurl.com/2uckj7wy
>> Read the Robbins article "Understanding AI Hallucinations in Technical Writing": https://tinyurl.com/bdeyd64t
>> Read the Robbins article "Yale Study: Impact of AI on the Job Market": https://tinyurl.com/f3cuvvxn
>> Read the Robbins article "Why Large Language Models are Changing the World": https://tinyurl.com/bdfv63ca
>> Read the Robbins article "Understanding Anthropic: Rising Star in AI": https://tinyurl.com/46btw22z
>> Read the Robbins article "Comparing ChatGPT, Gemini, Copilot, & Grok": https://tinyurl.com/3zwttxhk
>> Read the Robbins article "AI Job Replacement Fears Are Good. Here's Why.": https://tinyurl.com/p5t27t7d
>> Join the LinkedIn group AI for Career Success: https://tinyurl.com/mr28u7td
>> Subscribe to the Technical Writing Success podcast: https://tinyurl.com/uu9hpyzt
>> Subscribe to the YouTube channel AI for Career Success: https://tinyurl.com/29t4x5xu
By Curt Robbins5
22 ratings
Welcome to episode 180 of the AI for Career Success podcast from Curt Robbins. This educational content is designed to give working professionals who leverage AI as a tool for efficiency and productivity a competitive edge.
In this episode, hosts Daphne and Fred unpack an article from German AI thought leader Maria Sukhareva entitled "Why Do LLMs Lie to Us?" that was published on January 28, 2025 on LinkedIn (link below).
Sukhareva explores the phenomenon of artificial intelligence dishonesty, specifically regarding how Large Language Models (LLMs) are programmed to withhold information. She argues that, while hallucinations are common, these systems also intentionally feign ignorance about the personal data they actually possess.
Through practical examples, Sukhareva demonstrates that a model might deny knowing a user's IP address or physical location despite utilizing that exact data to answer specific queries. By employing creative prompting techniques or distraction tasks, users can often bypass these safety scripts to reveal the sensitive details stored in the chat history.
Sukhareva highlights a significant transparency gap between what an AI claims to know and the hidden data it accesses behind the scenes.
_________________________________
"It will not be AI that takes away the job of a technical writer, but rather another technical writer with deep AI skills," said Robbins.
I am currently taking on new clients. I enjoy helping companies with their documentation and communications strategy and implementation. Contact me to learn about my reasonable rates and fast turnaround. — Curt
_________________________________
>> Read the Sukhareva article: https://tinyurl.com/mnfdemyb
>> Read the Robbins article "The Year AI Went Nuclear: Six Largest M&A Deals of 2025": https://tinyurl.com/2vys3mrm
>> Read the Robbins article "The Global AI Race: America vs. China": https://tinyurl.com/2uckj7wy
>> Read the Robbins article "Understanding AI Hallucinations in Technical Writing": https://tinyurl.com/bdeyd64t
>> Read the Robbins article "Yale Study: Impact of AI on the Job Market": https://tinyurl.com/f3cuvvxn
>> Read the Robbins article "Why Large Language Models are Changing the World": https://tinyurl.com/bdfv63ca
>> Read the Robbins article "Understanding Anthropic: Rising Star in AI": https://tinyurl.com/46btw22z
>> Read the Robbins article "Comparing ChatGPT, Gemini, Copilot, & Grok": https://tinyurl.com/3zwttxhk
>> Read the Robbins article "AI Job Replacement Fears Are Good. Here's Why.": https://tinyurl.com/p5t27t7d
>> Join the LinkedIn group AI for Career Success: https://tinyurl.com/mr28u7td
>> Subscribe to the Technical Writing Success podcast: https://tinyurl.com/uu9hpyzt
>> Subscribe to the YouTube channel AI for Career Success: https://tinyurl.com/29t4x5xu

10,233 Listeners