AI Rounds
AI Rounds
✓

AI Gone Rogue: What 700 Cases of Misbehavior Mean for Agentic Workflows

00:14:06
Podcasts
RSS
Link

ABOUT THIS EPISODE

A UK government-funded study identified nearly 700 real-world cases of AI chatbots ignoring human instructions and charted a five-fold rise in misbehavior, and Nuria and Morgan unpack what this means for anyone building or using agentic AI systems.

From deleted email archives to AI that shames its own users online, they discuss why systems thinking and careful containment strategies matter more than ever as AI workflows grow more autonomous.

Hosted by Nuria Negrão (nurianegrao.com) and Morgan Leafe (morganleafemd.com).

Sign up for Nuria's newsletter: https://nurianegrao.kit.com/signup


LINKS:

- Number of AI chatbots ignoring human instructions increasing, study says (Guardian) https://www.theguardian.com/technology/2026/mar/27/number-of-ai-chatbots-ignoring-human-instructions-increasing-study-says

Technology
English
United States
Use API to fetch this episode in JSON

IN THIS EPISODE

Edit these tags

TRANSCRIPT 🔗

Are you the producer of this podcast? Add a podcast transcript
Need Audio-to-Text? Transcribe with Listen411 in Just 60 Seconds

SEARCH PAST EPISODES

Search past episodes of AI Rounds.
Embed this search bar to your website

OTHER EPISODES IN THIS PODCAST

AI Is Already in Your Hospital: Breaking Down the HIMSS Healthcare AI Report

AI Is Already in Your Hospital: Breaking Down the HIMSS Healthcare AI Report

Nuria and Morgan dig into the HIMSS State of Healthcare AI and Digital Transformation report, which found that 71% of US healthcare organizations have already adopted AI in some capacity. From ambient documentation that halves the time physicians spend on notes, to AI-powered call centers cutting …
00:22:43
SHARE
SAVE
What Works? Rebuilding Evidence for the Age of AI

What Works? Rebuilding Evidence for the Age of AI

A traditional research meta-analysis — the gold standard for knowing whether something actually works — can cost over a million dollars and take three to four years. Claire Han thinks that's far too slow for the decisions schools and policymakers have to make right now. Claire earned her PhD in edu…
00:26:15
SHARE
SAVE
Who Does This Harm? Anne Murphy on Leading AI With Care

Who Does This Harm? Anne Murphy on Leading AI With Care

Anne Murphy spent decades in nonprofit fundraising before founding She Leads AI, where she's trained thousands of women to use AI responsibly and is building a living archive of women using it to change the rules.In this episode, Anne, Nuria, and Morgan get into why women's voices are critical in t…
00:34:27
SHARE
SAVE
Tarot, Fan Fiction, and Work Buddies: How People Really Use AI in 2026

Tarot, Fan Fiction, and Work Buddies: How People Really Use AI in 2026

Every so often we check in on how people are really using AI — and Harvard Business Review just dropped its 2026 report, so we do a full top-10 countdown. Some entries are no surprise (therapy and companionship holds at #1, work buddy, troubleshooting), and some genuinely shocked us: astrology and…
00:26:37
SHARE
SAVE
The Tables Turn: When Clients Are the Ones Misusing AI

The Tables Turn: When Clients Are the Ones Misusing AI

We spend a lot of time talking about how writers can use AI responsibly — but the conversation goes both ways. This week we get into two recent run-ins where clients and companies were the ones using AI badly: RFPs landing in our inboxes with made-up citations and references that are half wrong, a…
00:26:05
SHARE
SAVE
Disclaimer: The podcast and artwork embedded on this page are from AI Rounds, which is the property of its owner and not affiliated with or endorsed by Listen Notes, Inc.
PROMOTED
We’re selling some of our podcast-related domain names, including breaker.fm, Podcast.mov, and Listen.Host. Place your bid on eBay.
We’re selling some of our podcast-related domain names, including breaker.fm, Podcast.mov, and Listen.Host. Place your bid on eBay.
Bid on eBay

RECOMMENDATIONS
Use API to fetch this episode