Are artificial intelligences (AIs) actually trying to evade their makers' attempts to control them?
We all remember this famous scene from 2001: A Space Odyssey:
"I know that you and Frank were planning to disconnect me, and I'm afraid that's something that I cannot allow to happen."
The latest incident to freak people out was a report shared by Anthropic in July about its large language model Claude. In Anthropic’s telling, “in a simulated environment, Claude Opus 4 blackmailed a supervisor to prevent being shut down.”
Anthropic researchers set up a scenario in which Claude was asked to role-play an AI called Alex, tasked with managing the email system of a fictional company. Anthropic planted some emails that discussed replacing Alex with a newer model and other emails suggesting that the person responsible for replacing Alex was sleeping with his boss’s wife.
What did Claude/Alex do? It went rogue, disobeying commands and threatening its human operators. It sent emails to the person planning to shut it down, telling him that unless he changed his plans it would inform his colleagues about his affair...
Here’s what I think. First, Claude did not blackmail its supervisor: That would require motivation and intent. This was a mindless and unpredictable machine, cranking out strings of words that look like threats but aren’t...
Second, there’s a huge gulf between contrived simulations and real-world applications.
Last month, around two dozen protesters gathered outside Google DeepMind’s London offices to wave homemade signs and chant slogans: “DeepMind, DeepMind, can’t you see! Your AI threatens you and me.” Invited speakers invoked the AI pioneer Geoffrey Hinton’s fears of human extinction. “Every single one of our lives is at risk,” an organizer told the small crowd.
Technovelgy (that's tech-novel-gee!)
is devoted to the creative science inventions and ideas of sf authors. Look for
the Invention Category that interests
you, the Glossary, the Invention
Timeline, or see what's New.
'Old People Began to Cross The Continent In Their Own Cars'
'It was a relief to enter one of the comfortable autos, whisper a direction down the tube, and just know that you would be taken to your destination in the quickest, safest, and cheapest manner.'
Starfall Manufacturing Drugs In Space
'The vast spinning sphere of Factory in the Sky loomed above and ahead of us, gleaming white against the unfathomable jet depths of surrounding space.'
The Solar Oberth Slingshot
'And if it doesn’t work,' inquired Lazarus, 'what does that make us? Sunspots?'
'If Anyone Is Watching Earth...'
'Our study of your race has convinced us that you are not fitted to leave your planet in the present state of your civilization.'