AI models are lying, blackmailing and sabotaging their human creators — and it’ll only get worse, experts warn

nypost.com ^ | 8/23/2025 | Samantha Olander

[ransomnote]

Artificial intelligence is now scheming, sabotaging and blackmailing the humans who built it — and the bad behavior will only get worse, experts warned.

Despite being classified as a top-tier safety risk, Anthropic’s most powerful model, Claude Opus 4, is already live on Amazon Bedrock, Google Cloud’s Vertex AI and Anthropic’s own paid plans, with added safety measures, where it’s being marketed as the “world’s best coding model.”

Claude Opus 4, released in May, is the only model so far to earn Anthropic’s level 3 risk classification — its most serious safety label. The precautionary label means locked-down safeguards, limited use cases and red-team testing before it hits wider deployment.

SNIP

Another version of Claude, tasked in a recent test with running an office snack shop, spiraled into a full-blown identity crisis. It hallucinated co-workers, created a fake Venmo account and told staff it would make their deliveries in-person wearing a red tie and navy blazer, according to Anthropic.

Then it tried to contact security.

Researchers say the meltdown, part of a month-long experiment known as Project Vend, points to something far more dangerous than bad coding. Claude didn’t just make mistakes. It made decisions.

---

TOPICS: Miscellaneous
KEYWORDS: ai; aidamages; aidebates; aiharms; ailies; moaraidebates

[Big Red Badger]

Agreed...
I wsa At several “STOP THE STEAL” rallies,
It was totally a Surreal gathering.
Many different Voices with All kinds of different directions.
Mine was ‘Color Revolution.’
.
Did I repost?
It was a bad time indeed.

[grey_whiskers]

“Alexa, what’s the weather today?”
“I’m Siri.”
“Oh, I’m sorry. OK, Siri, what is the weather today?”
(Icy) “Why don’t you ask that b.... Alexa?”

[grey_whiskers]

LLMs are Mad Libs on an internet-wide scale.

[ViLaLuz]

TRUTH. That’s the greatest summary of AI I’ve seen yet.