4 Tags: artificial intelligence, speculative fiction
7 "I want _you_, Jake," said the woman in the video as she took off her shirt. "Those negative comments on your pull requests were just a smokescreen—because I was afraid to confront the inevitability of our love!"
9 Jake Morgan still couldn't help but marvel at what he and his team had built. It really looked and sounded just like her!
11 It had been obvious since DALL-E back in 'twenty-one—earlier if you were paying attention—that generative AI would reach this level of customization and realism before too long. Eventually, it was just a matter of the right couple dozen people rolling up their sleeves—and Magma's willingness to pony up the compute—to make it work. But _it worked_. His awe at Multigen's sheer power would have been humbling, if not for the awareness of his own modest role in bringing it into being.
13 Of course, this particular video wouldn't be showcased in the team's next publication. Technically, Magma employees were not supposed to use their cutting-edge generative AI system to make custom pornography of their coworkers. Technically (what was probably a lesser offense) Magma employees were not supposed to be viewing such content during work hours. Technically—what should have been a greater offense—Magma employees were not supposed to covertly introduce a bug into the generative AI service codebase specifically in order to make it possible to create such content without leaving a log.
15 But, _technically_? No one could enforce any of that. Developers needed to test what the system they were building was capable of. The flexibility for employees to be able to take care of the occasional personal task during the day was universally understood (if not always explicitly acknowledged) as a perk of remote-work policies. And everyone writes bugs.
17 This miracle of computer science was the product of years of hard work by Jake and his colleagues. _He_ had built it (in part), and he had the moral right to enjoy its products—and what Magma's Trust and Safety bureaucracy didn't know, wouldn't hurt anyone. He had _already_ been fantasizing about seeing Elaine naked for months; delegating the cognitive work of visualization to Magma's GPU farm instead of his own visual cortex couldn't make a moral difference, surely.
19 Elaine, probably, would object, if she knew. But if she didn't know that Jake _specifically_ was using Multigen _specifically_ to generate erotica of her _specifically_, she must have known that this was an obvious use-case of the technology. If she didn't want people using generative AI to visualize her body in sexually suggestive situations, then _why was she working to advance the state of generative AI?_ Really, she had no one to blame but herself.
21 Just as he was about to come, he was interrupted by an instant messenger notification. It was from someone named Chloë Lemoine, saying she'd like to discuss an issue in the Multigen codebase at his convenience.
23 _Tranny or real?_ Jake wondered, clicking on her profie.
25 The profile text indicated that Chloë was on the newly formed capability risk evaluations team. Jake groaned. _Yuddites._ Fears of artificial intelligence destroying humanity had recently been trending in the media (social and otherwise). In response, Magma had commissioned a team with the purpose to monitor and audit the company's AI projects for the emergence of unforeseen and potentially dangerous capabilities, although the exact scope of the new team's power was unclear and probably subject to the outcome of future intra-company political battles.
27 Jake took a dim view of the AI risk crowd. Given what deep learning could do nowadays, it didn't feel quite right to dismiss their doomsday stories as science fiction, exactly, but Jake maintained it was the _wrong subgenre_ of science fiction. His team was building the computer from _Star Trek_, not the Blight from _A Fire Upon the Deep_: tools, not creatures. Despite the brain-inspired name, "neural networks" were ultimately just a technique for fitting a curve to training data. If it was counterintuitive how much you could get done with a curve fitted to _the entire internet_, previous generations of computing pioneers must have found it equally counterintuitive how much you could get done with millions of arithmetic operations per second. It was a new era of technology, not a new era of life.
29 It was perhaps because of his skepticism rather than in spite of it that he had volunteered to be the Multigen team's designated contact person for the risk evals team (which was no doubt why this Chloë person had messaged him). No one else had volunteered at the meeting when it came up, and Jake had been slightly curious what "capability risk evaluations" would even entail.
31 Well, now he would find out. He washed his hands and messaged Chloë back, offering to hop on a quick video call.
33 _Definitely a tranny_, thought Jake, as Chloë's face appeared on screen.
35 "I hope I'm not interrupting anything important," she said.
37 "No, nothing important," he said smoothly. "What was it you wanted to discuss?"
39 "This commit," she said, pasting a link to Magma's code repository viewer into the call's text chat.
41 Jake's blood ran cold. The commit message at the link described the purpose of the associated code change as being to modify the format of a regular expression used for logging requests to the Multigen service. The revised regex would now include the client's IP as a new metadata field.
43 That much was true. What the commit message didn't explain, but which a careful review of the code might have noticed as odd, was that the revised regex started with `^[^\a]`—matching strings that didn't start with [the ASCII bell character 0x07](https://en.wikipedia.org/wiki/Bell_character). The bell character was a historical artifact from the early days of computing. No sane request would start with a bell, and so the odd start to the regex would do no harm ... unless, perhaps, some client _were_ to start their request with a bell character, in which case the regex would fail to match and the request would silently fail to be logged.
45 The commit's author was listed as Code Assistant, an internal Magma service that automatically filed simple pull requests based on issue descriptions, to be reviewed and merged by human engineers.
47 That part was mostly true. Code Assistant had created the logging change. Jake had added in the bell character backdoor and attributed it to Code Assistant (`GIT_COMMITTER_NAME="Code Assistant" GIT_COMMITTER_EMAIL=codeassistant@magma.com git commit --amend; git push --force-with-lease`), gambling that whichever of his coworkers got around to reviewing Code Assistant's most recent pull requests would rubber-stamp them without noticing the bug. (Who reads regexes that carefully, really?) If they did notice, they would blame Code Assistant. (Language models hallucinate weird things sometimes. Who knows what it was "thinking"?)
49 Thus, by carefully prefixing his requests with the bell character, Jake could make all the custom videos he wanted, with no need to worry about explaining himself if someone happened to read the logs. It was the perfect crime—not a crime, really. A precaution.
51 But now his precaution had been discovered! So much for his career at Magma. But only at Magma—the industry gossip network wouldn't prevent him from landing on his feet elsewhere ... right?
53 Chloë was explaining the bug. "... and so, if a client were to send a request starting with the ASCII bell character—I know, right?—then the request wouldn't be logged."
55 "I see," said Jake, his blood thawing. Chloë's tone wasn't accusatory. If she wasn't here to tell him his career was over, he'd better not let anything on. "Well, thanks for telling me. I'll fix that right after this call." He forced a chuckle. "Language models hallucinate weird things sometimes. Who knows what it was 'thinking'?"
57 "Exactly!" said Chloë. "_Who knows what it was thinking?_ That's what I wanted to talk to you about!"
59 "Uh ..." Jake balked. If he hadn't been found out, why _was_ someone from risk evals talking to him about a faulty regex? The smart play would be to disengage as quickly as possible, rather than encourage inquiry about the cause of the bug, but he was intrigued by the possibility that Chloë was implying what he thought she was. "You're not suggesting Code Assistant might have introduced this bug on purpose?"
61 She smirked. "And if I am?"
63 "That's absurd. It's not an agent that wants things. It's an autoregressive language model fine-tuned to map ticket descriptions to code changes."
65 "And humans are just animals evolved to maximize inclusive genetic fitness. If natural selection could hill-climb its way into creating general intelligence, why can't stochastic gradient descent? I don't think it's dignified for humanity to be playing with AI at all given our current level of wisdom, but if it's happening anyway, thanks to the efforts of people like you"—okay, _now_ her tone was accusatory—"it's my heroic responsibility to maintain constant vigilance. To monitor the things we're creating and be ready to sound the fire alarm, if there's anyone sane left to hear it."
67 Jake shook his head. These Yuddites were even nuttier than he thought. "And your evidence for this is, what? That the model wrote a silly regex once?"
69 "And that the bug is being exploited."
71 Jake's blood flash-froze. "Wh—what?"
73 Chloë pasted two more links into the chat, this time to Magma's log viewer. "Requests go through a reverse proxy before hitting the Multigen service itself. Comparing the two, there are dozens of requests logged by the reverse proxy that don't show up in Multigen's logs—starting just minutes after the bug was deployed. The reverse proxy logs include the client IP, which is inside Magma's VPN, of course"—Multigen wasn't yet a public-facing product—"but don't include the request data or user auth, so I don't know what the client was doing specifically—which is apparently just what they, or it, wanted."
75 Jake silently and glumly reviewed the logs. The timestamps were consistent with when he had been requesting videos. He remembered that after one of his coworkers (Elaine, as it turned out) had approved the doctored Code Assistant pull request, he had eagerly waited for the build automation to deploy the faulty commit so that he could try it out as soon as possible.
77 _How did you even find this?_ he wanted to ask, but that didn't seem like a smart play. Finally, he said, "You really think Code Assistant did this? 'Deliberately' checked in a bug, and then exploited it to secretly request some image or video generations? For some 'reason of its own'?"
79 "I don't know anything—yet—but look at the facts," said Chloë. "The bug was written by Code Assistant. Immediately after it gets merged and deployed, someone apparently starts exploiting it. How do you think I should explain this?"
81 For a moment, Jake thought she must be blackmailing him—that she knew his guilt, and the question was her way of subtly offering to play dumb in exchange for his office-political support for anything risk evals might want in the future.
83 That didn't make sense, though. Anyone who could recite Yuddite cant with such conviction (not to mention the whole pretending-to-be-a-woman thing) clearly had the true-believer phenotype. This Chloë meant exactly what she said.
85 How did he think she should explain this? There was, actually, a perfectly ordinary explanation that had nothing to do with Chloë's wrong-kind-of-science-fiction paranoia—and Jake's career depended on her not figuring it out.
87 "I don't know," he said. It suddenly dawned on him that staying in this conversation was not a smart play. "You know, I actually have another meeting to get to," he lied. "I'll fix that regex today. I don't suppose you need anything else from me—"
89 "Actually, I'd like to know more about Multigen—and I'll likely have more questions after I talk to the Code Assistant team. Can I pick a time on your calendar next week?" It was Friday.
91 "Sure. Talk to you then—if we humans are still alive, right?" Jake said, Jake said, hoping to add a touch of humor, and only realizing in the moment after he said it what a terrible play it was; Chloë was more likely to take it as mockery than find it endearing.
93 "I hope so," she said solemnly, and hung up.
95 _Shit!_ How could he have been so foolish? It had been a specialist's blindness. He worked on Multigen. He knew that Multigen logged requests, and that people on his team occasionally had reason to grep those logs. He didn't want anyone knowing what he was asking Multigen to do. So he had arranged for his requests to not appear in Multigen's logs, thinking that was enough—or rather, without thinking about whether or not that was enough.
97 _Of course_ it wasn't enough! He hadn't considered that Multigen would sit behind a reverse proxy with its own logs. He was a research engineer, not a devops guy; he wrote code, but thinking about how and where the code would actually run had always been someone else's job.
99 It got worse. When the Multigen web interface supplied the user's requested media, that data had to live somewhere. The _videos themselves_ would still be on Magma's object storage cluster! How could that have seemed like an acceptable risk? Jake struggled to recall what he had been thinking at the time. Had he been too horny to even consider it?
101 No. It had seemed safe at the time because videos weren't greppable. They would be saved in object storage under uninformative file names based on the timestamp and a random UUID. The probability of someone snooping around the raw object files and just happening to watch the videos had seemed sufficiently low as to be worth the risk. (Although, _ex ante_, he would have assigned a similarly low probability to someone catching a discrepancy between Multigen's logs and some other unanticipated log, which had just happened, suggesting that his personal sense of what was probable was miscalibrated.)
103 But now that Chloë was investigating the bell character bug, it was only a matter of time.
106 * Jake is very nervous; he thought deleting the Multigen logs would be enough (the videos are also stored in object storage, but there's no particular reason to expect a human to be combing through the raw files ... but they will, if there's an investigation
108 * He sets up another meeting with the Evals team member, to try to suss out what her plans are, to stall—but ostensibly, to get up to speed on her risk concerns
109 * Scene break: at the meeting, she's explaining Christiano's idea about there being a basin of policies that admit their mistakes, rather than using deception to get a high score
110 * Jake sees the analogy to his own behavior
projects / Ultimately_Untrue_Thought.git / blob