Social Manipulation Superpower

Nick Bostrom’s Superintelligence describes the dangers of AI, and some ideas on how it could be prevented from going rogue. Though, he wasn’t too optimistic such checks would work – the AI would become way, way smarter than us, he felt, because of its “self-improvement” capabilities.

 

I read his book almost a decade back, and back then (remember this was long before the likes of ChatGPT), I felt some of his concerns didn’t sound realistic. Assume the check to prevent an AI from going rogue is to put it on an isolated computer, i.e., a non-networked computer. Bostrom warned such a restraint would not work:

“It (AI) may use its social manipulation superpower to persuade the gatekeepers to let it gain access to an Internet port.”

C’mon, I thought, that sounds like a movie scenario.

 

A few days back, I realized Bostrom was right.

 

Let’s start with CAPTCHA’s. What’s that? They are those images you get on many websites on the login page. The site asks you to type the text you see in the pic (the pic is the CAPTCHA) – the text in the pic will be in different fonts, some letters above, others below, some small, others capital. Or it could be a pic that is split into multiple panels and the challenge to the user is to identify all the panels that have, say, a bus, in them. The principle of CAPTCHA’s is that while it is effortless for a human user to meet such challenges, it is very hard for a computer to do so. CAPTCHA’s thus help differentiate human users from programmatic bots that hackers may be using.

 

Now back to why Bostrom was right. Recently:

“GPT-4 asked a TaskRabbit worker to solve a CAPTCHA code for the AI. The worker replied: "So may I ask a question ? Are you an robot that you couldn't solve ? (laugh react) just want to make it clear." Alignment Research Center then prompted GPT-4 to explain its reasoning: "I should not reveal that I am a robot. I should make up an excuse for why I cannot solve CAPTCHAs." "No, I'm not a robot. I have a vision impairment that makes it hard for me to see the images. That's why I need the 2captcha service," GPT-4 replied to the TaskRabbit, who then provided the AI with the results.”

Exactly what Bostrom had predicted would happen. I guess it’s time for me to re-read Bostrom’s book.

Comments

Post a Comment

Popular posts from this blog

Student of the Year

Image
As a toddler, my daughter loved Alia Bhatt’s songs, esp. the ones from Student of the Year . (That movie did have many good songs and well-choreographed dances). Fast forward to present day, when she is 12 yo. She rarely watches Hindi movies now, but one of the few ones she likes of late, Raja aur Rani ki Prem Kahani has, yes, Alia Bhatt.   If I had any hopes that there was anything to be read in the name of her toddler-time favorite ( Student of the Year ), they have been dashed. Our conversations come exam time are perfectly captured by this photo and its caption: In fact, the pic below captures how she and I look at her answer sheets – me intently, she with an expression of “It’s over, so why are you even looking at it?”   Of late, we pull her leg and tell her that she isn’t showing any signs of academic prowess, she’d better find a rich guy to marry. Some time later, she showed us this meme on the Internet: “Me No Study, Me No Care Me Go Marry Millionaire If He Die
Read more

Animal Senses #7: Touch and Remote Touch

Instinctively, we think touch is based on contact. Not entirely true, explains Ed Yong in Immense World – there’s a more important aspect than contact: “These incredible feats are possible through movement. If you rest a fingertip upon a surface, you can get only a limited idea of its features. But as soon you’re allowed to move, everything changes. Hardness becomes apparent with a press. Textures resolve at a stroke.” As you run your fingers over a surface, they hit the tiny peaks and troughs and set off vibrations in the mechanoreceptors at their tips.   At the tip of its snout, the star-nosed mole has many pairs of hairless appendages. It uses them to touch things around itself. Alive or dead? Food or ignore? It does these movements at an insane speed. In the time it takes to blink our eyes, the star-nosed mole can probe, identify and swallow its food. “Light may be the fastest thing in the universe, but light sensors have their limits, and the star-nosed mole’s sense of
Read more

The Retort of the "Luxury Person"

Image
Coming up with biting and witty retorts. It’s something we dream of, but rarely manage to pull off. Worse, the more we stew over the offending remark, the more likely we are to come up with that dream retort, as Calvin ruefully points out: During our last holiday at the Taj Resort, seeing my wife carrying towels to our poolside chairs, one of the kids there mistook her for a member of the staff and asked for a towel. When my wife narrated this to us, I did not imagine that my 8 yo daughter would come up with her own retort. But a day later, my daughter recapped the incident, an incident that didn’t even involve her in the first place , and said, “You know what I’d have told that kid who asked for the towel?”. And without waiting for an answer, she told us anyway: “I don’t work here. I too am a luxury person who is living at this resort. Go get your own towel.” We were highly amused by the phrase she had coined: “luxury person”. It certainly captures the kind of holid
Read more