Posts

At both of my last two jobs I was faced with a task that seemed insurmountable: identify and block fraudulent activity. Many commercial tools exist, but none are particularly suited to the job. At Ticketmaster I learned the lessons I would carry to Weedmaps—that success requires customized workflows for identifying and remediating malicious, non-human traffic. At both Ticketmaster and Weedmaps, we faced the same adversaries: bots, scrapers, fraudulent reviews, and other forms of malicious automation. While the request seemed deceptively simple, the task was Sisyphean at best and Kafkaesque the rest of the time. How do you find a needle in a haystack? Easy—burn the hay and use a magnet. But this was more like finding one particular needle in a stack of needles, without knowing what made that needle unique. ...

Introducing Recursive Output Trust Attacks (ROTA), a novel class of LLM jailbreaks exploiting model self-trust.

We stand at the threshold of a new era, one where code running on distributed machines is programmed to think, work, and even create for us. A world in which a few dozen billionaires fund self-writing code to program robots—made in factories they own. We could be at the precipice of a utopia, an anti-capitalist nirvana—no longer beholden to the day’s labor equaling a day’s ration. This potential reality is a dream as old as the words of John the Revelator and Thomas Aquinas. Or perhaps we stand at the brink of destruction, blinded by hubris and shareholder greed. ...