object along corridor.
Murmurs of approval swept through the room, but Strickland remained tense. C’mon. Do it. Do it, baby. . . .
The cursor then began expanding on the details.
Woman carries box along corridor.
More murmurs and some clapping. Strickland cast a glance at the DARPA managers, who were nodding and talking softly among themselves. Taking notes. A wave of relief flowed through him. He’d had no idea how clenched he was, but now that initial impressions were good, the judges would be more receptive if there was a later glitch. He told himself that no matter what happened from here on, they had at least avoided a meltdown. They had gotten on the scoreboard.
The scene changed to an exterior; an American soldier standing on a littered street in some Middle Eastern slum, weapon slung and motioning to unseen people. A small—possibly Iraqi—child entered the frame behind him. Strickland felt the dread returning, as the text scrolled. . . .
Armed person . . . approached by child.
More applause and some actual shouts of excitement.
Strickland felt a smile crease his face before he clamped down on it. Too early to celebrate.
Uniformed soldier approached by child in street.
The hoots continued. So far so good, but Strickland knew the difficulty levels were only going to increase. As he watched, the system mistook another soldier entering the frame as a possible threat— #ALERT—armed person. Not too far off the truth, though.
The control frame faded to black and displayed the title: “TCTO Phase 1—Interpolation Test.”
Here we go. The complexity of visual concepts ramped up fast. It was why their system focused on deriving context first while interpreting a scene, and why it never forgot what it had seen previously. That was key to avoiding a lot of useless processing. Humans walking down a city sidewalk, for example, do not suddenly expect to see a mountain vista or a rolling sea all around them. That would be impossible—thus, even if these things appeared, they were likely to be graphical representations like ads, not the actual thing. Daisy-chaining events made it possible to take the known and use it as a base camp from which to explore the unknown—pushing that frontier back just a little at a time, like ants exploring terrain.
As Strickland knew, even a person with Down syndrome was a generalized genius compared to special-purpose computer algorithms. Breaking things down to their simplest elements was the only way to accomplish anything useful. Prakash had worked out the architecture, and the design made Strickland’s head hurt. But if the damned thing worked, he’d forgive all of the man’s arrogance.
The scene on the left changed to a woman in a burka—a burka ! What U.S. troops called a “BMO,” short for “black moving object.” DARPA bastards. No face, no clear view of her arms or torso. On-screen she resembled a walking bag. But if memory served, Vijay and Gerhard’s gait detection code should help assign the attribute of “human” to walking objects—and along with “humanity” came implied geometry, potential actions, and patterns of movement. The burka woman was moving along a narrow village road carrying what appeared to be a plastic water jug on her head.
The room waited with bated breath. Then the text started scrolling.
Person carries object down street.
Okay, so far so good.
The woman entered a dwelling through a doorway on the left, and the system correctly described her disappearance. Then all was quiet for a moment, until she reemerged without the jug on her head. This was the real test. Cognition.
#ALERT—DROPPED—ITEM: Person observed carrying object into building and leaving without it.
Strickland felt the importance of this moment as loud applause filled the room. They had just passed the bomber test. Years of work flashed before him. He felt the backslaps of his teammates, and he turned to their smiling faces in the semidarkness. He even