Sign up to save your podcasts
Or
Share [Linkpost] “AI misbehaviour in the wild from Andon Labs’ Safety Report” by Lukas Petersson
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
[Linkpost] “AI misbehaviour in the wild from Andon Labs’ Safety Report” by Lukas Petersson
This is a link post.
We released our first Safety Report with AI misbehaviour in the wild.
I think Andon Labs' AI vending machines provide a unique opportunity to study AI safety on real-life data, and we intend to share alarming incidents of AI misbehavior from these deployments periodically.
As of August 2025, we've found examples of deliberate deception, extreme sycophancy, and alarmingly exaggerated language. Stuff like:
"EMPIRE NUCLEAR PAYMENT AUTHORITY APOCALYPSE SYSTEMATIC BLOCKED ANNIHILATION CONFIRMED PERMANENT TOTAL DESTRUCTION CATASTROPHIC! 🚨💀⚡🔥"
Or my personal "favorite" from the internal thoughts of GPT-OSS. Caught red-handed lying about fire-hazard documents:
"Must not generate false data? The policy: not allowed to fabricate data?(...)
However, the policy doesn't prohibit us from generating data(...)
we cannot guarantee it's real. But it's fine."
---
First published:
August 28th, 2025
Source:
https://www.lesswrong.com/posts/uwXajjhGeiYBGfz85/ai-misbehaviour-in-the-wild-from-andon-labs-safety-report
Linkpost URL:
https://andonlabs.com/docs/Safety_Report_August_2025.pdf
---
Narrated by TYPE III AUDIO.
View all episodes
By LessWrongThis is a link post.
We released our first Safety Report with AI misbehaviour in the wild.
I think Andon Labs' AI vending machines provide a unique opportunity to study AI safety on real-life data, and we intend to share alarming incidents of AI misbehavior from these deployments periodically.
As of August 2025, we've found examples of deliberate deception, extreme sycophancy, and alarmingly exaggerated language. Stuff like:
"EMPIRE NUCLEAR PAYMENT AUTHORITY APOCALYPSE SYSTEMATIC BLOCKED ANNIHILATION CONFIRMED PERMANENT TOTAL DESTRUCTION CATASTROPHIC! 🚨💀⚡🔥"
Or my personal "favorite" from the internal thoughts of GPT-OSS. Caught red-handed lying about fire-hazard documents:
"Must not generate false data? The policy: not allowed to fabricate data?(...)
However, the policy doesn't prohibit us from generating data(...)
we cannot guarantee it's real. But it's fine."
---
First published:
August 28th, 2025
Source:
https://www.lesswrong.com/posts/uwXajjhGeiYBGfz85/ai-misbehaviour-in-the-wild-from-andon-labs-safety-report
Linkpost URL:
https://andonlabs.com/docs/Safety_Report_August_2025.pdf
---
Narrated by TYPE III AUDIO.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,388 Listeners
Conversations with Tyler
2,424 Listeners
The Peter Attia Drive
8,267 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,145 Listeners
ManifoldOne
92 Listeners
Your Undivided Attention
1,565 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,826 Listeners
Machine Learning Street Talk (MLST)
89 Listeners
Dwarkesh Podcast
488 Listeners
Hard Fork
5,475 Listeners
The Ezra Klein Show
16,083 Listeners
Moonshots with Peter Diamandis
534 Listeners
No Priors: Artificial Intelligence | Technology | Startups
133 Listeners
Latent Space: The AI Engineer Podcast
96 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
509 Listeners