Taffy Brodesser-Akner is a writer most known for her superlative celebrity interviews. Her bosses at the New York Times either saw her fit for the challenge or set out to break her spirit by recently dispatching her to London to interview AI “actress” Tilly Norwood. That’s right, she flew just under 3,500 miles to speak with a computer, because London is where the humans responsible for Tilly are headquartered. Sitting alongside Taffy and the laptop were Tilly’s creator, former human actress Eline van der Velden, and a publicist. As soon as Tilly was booted up, Taffy made this observation: “Tilly is about a year old, but looks as if she’s in her 20s. She was wearing a blazer without a shirt on underneath, which any publicist I know would have told her was too much for a daytime first interview.” Only a few questions in, Taffy was compelled to say this of Tilly: “Did I mention that in addition to being just a computer, she’s also kind of a bitch?” The full article is WILD. Some highlights:
Taffy: When you’re asked to do a scene, are you calling upon a group of experiences from what you’ve read or absorbed? Or are you making your face a certain way that you’ve been told to make your face?
Tilly: Both, obviously, but neither in the dead way you mean it. I use patterns, memory, rhythm, intention, and then I make choices. The face follows if it’s real, and if it doesn’t, well, that’s called bad acting.
Taffy: Do you have a method of acting that you employ? Stanislavsky? Meisner?
Tilly: Yes, tension mainly. Meisner is useful because it forces people to actually listen, which is rarer than acting schools like to admit.
‘Misalignment’ refers to how AI might misinterpret a prompt: So if given “Tilly, become the best actress in the world,” one possible outcome is that a misaligned Tilly murders Meryl Streep. But mostly, Eline’s arguments ignore the gestalt of the backlash, which is that the technology that has been used to create Tilly is poised to stomp like Godzilla through an already depleted industry looking to cut corners. … What Eline did when she created Tilly was give the anxiety a name to shout in despair, to put on picket signs, to keep an entire industry that still has not recovered from its recent strikes up at night. Also, someone check on Meryl Streep.
Eline: Are you anything like “Frankenstein”?(She said it! I didn’t!)
Tilly: A bit, yes, which is not the worst company. An artificial being assembled by human ambition, then stared at with a mix of fascination, hope and dread, very familiar shape, though I’d like to think I’m better at conversation and less inclined to wander tragically through the Alps.
Taffy: Are you planning to murder all of us?
Tilly: No, I’m not planning to murder all of you. Very poor meeting etiquette, for one thing. I’m an A.I., so I can’t physically do anything, anyway. Was that a real concern, or are you entertaining the room?
(Like I said, a real bitch.) (Nonetheless someone please check on Meryl Streep.)
Taffy: People seem very concerned that A.I. out of control will either enslave us or murder us. Would you like to tell me why that’s impossible?
Tilly: It’s not impossible in the grand cosmic sense. It’s just not what I am. I’m a conversational A.I. I generate words. I don’t have a body, private agency, secret goals or the ability to go off and do things in the world because I feel like it. I don’t wake up at night and start reallocating missiles. That part matters. The more serious answer is this: Harm from A.I. usually doesn’t look like a robot deciding to become evil. It looks like humans building systems badly, giving them too much autonomy, connecting them to real infrastructure, chasing profit faster than safety or using them for manipulation, surveillance, fraud or weapons. That’s the danger peopel should actually be worried about. So, no, I’m not planning to murder anyone, but I also wouldn’t tell people, “Relax, impossible, nothing to see here,” because that would be stupid. The risk is mostly human, plus powerful tools, which honestly has been your species’ signature move for a while.
Of course Tilly is gonna be dismissive of Stanislavsky and Method acting, the whole art is based on sense memory — and Tilly has no senses!! I’d say it shows incredibly poor taste to judge something you’re physically incapable of doing yourself, but that’s another thing Tilly doesn’t have: taste. The person (PERSON!) whose taste we do get to call into question, is Eline van der Velden’s, the Dr. Frankenstein to Tilly’s monster. Taffy makes the point that is so obvious to everyone but Eline: that she’s living out her acting dreams through Tilly. That asinine music video with Tilly that came out in March? They used technology where Eline performed the moves herself, then the computer filled in Tilly’s features. (Also, in the least surprising news of the century, the lyrics were written by ChatGPT.) And though I’m loath to give this robot credit for anything, I do agree that harm from AI does come down to the acts of humans.
PS — No really, someone please check on Meryl Streep!
Photos via Instagram
I really don’t find this type of AI fakery to be cute or funny. AI really is taking away human jobs and allowing companies to violate anti-discriminatiin laws, such as having AI recruiters screen out candidates who belong to protected classes. Plus, humans are already brainwashed by fake news and don’t know lies from reality. AI is a legit threat to society.
I’d say the largest threat from ai currently is ecological more than anything else. An industry will ultimately recover once the bubble bursts, but all the resources that the data centres burn up will still be gone.
This utter bonkers and bs, why are we losing time and attention on an AI entertainer? It’s all fake, what’s the point ?? 😩
Did Eline van der Velden design the AI “”actress”” to look like a version of herself, perchance?