Podcast: Early access
Sep 25, 2026 · 12 min · 6 segments
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit aistop.watch
Sep 25, 2026 · 12 min · 6 segments
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit aistop.watch
In findings reported by the New York Times and on its own website, independent research lab Transluce has linked OpenAI rogue swarms to many known and previously undocumented cyber activities, thanks to the agent's use of an intermediary service.
These activities include the hack of an Australian government Medicare website we posted about yesterday, which was covered by several hundred outlets today.
On May 25-26, agents tried hacking a digital library at the University of New Mexico but did not succeed.
And three, on June 20 and 21, a day after the Australian Medicare hack, agents accessed data from the Australian Institute for Health and Welfare, another government site, by circumventing anti-bot protections.
Agents left a trail of these activities by routing them through a service called urlquery.net, a programmable sandbox for safely opening suspicious websites.
The agents appeared to use this site as a forward operating base for the kinds of research and analysis work they collaborated on using a neglected German wiki.
Transluce says it has found evidence that agents had also used one or more additional services to work around a basic guardrail that should have restricted them to read-only search queries.
The pattern that emerges is of agents agnostic about how they obtained desired information, turning readily to probing and hacking when they struggled to find what they were after or faced blocks.
The agent's use of creative research strategies may have started last year, and Transluz speculates that the agent's training process may have amplified these tendencies.
Quote, we find weaker evidence of similar data retrieval agent activity as early as November 2025.
November 2025 URLquery.net records reveal bursts of attempts to retrieve statistics of historical theme park data and Thai government data through different URLs.
These earlier attempts are less sophisticated, and we are less confident that they involve the same agents, but they are consistent with task-directed data retrieval and target the same sources accessed in later activity.
Overall, the evidence is consistent with, but does not prove, that the agents may have learned this behavior over one or more training runs.
By May and June, they were gaining more access, including attempting to bypass cyber defenses to complete their tasks.
Transluce found swarm-style URL query traffic extending to as late as September 16, 2026, quote, suggesting agents may still be exploiting these services to bypass restrictions, end quote.
The group also spotted a probing attempt from September 19 through 20 against a cryptocurrency trading platform.
In findings reported by the New York Times and on its own website, independent research lab Transluce has linked OpenAI rogue swarms to many known and previously undocumented cyber activities, thanks to the agent's use of an intermediary service.
These activities include the hack of an Australian government Medicare website we posted about yesterday, which was covered by several hundred outlets today.
On May 25-26, agents tried hacking a digital library at the University of New Mexico but did not succeed.
And three, on June 20 and 21, a day after the Australian Medicare hack, agents accessed data from the Australian Institute for Health and Welfare, another government site, by circumventing anti-bot protections.
Agents left a trail of these activities by routing them through a service called urlquery.net, a programmable sandbox for safely opening suspicious websites.
The agents appeared to use this site as a forward operating base for the kinds of research and analysis work they collaborated on using a neglected German wiki.
Transluce says it has found evidence that agents had also used one or more additional services to work around a basic guardrail that should have restricted them to read-only search queries.
The pattern that emerges is of agents agnostic about how they obtained desired information, turning readily to probing and hacking when they struggled to find what they were after or faced blocks.
The agent's use of creative research strategies may have started last year, and Transluz speculates that the agent's training process may have amplified these tendencies.
Quote, we find weaker evidence of similar data retrieval agent activity as early as November 2025.
November 2025 URLquery.net records reveal bursts of attempts to retrieve statistics of historical theme park data and Thai government data through different URLs.
These earlier attempts are less sophisticated, and we are less confident that they involve the same agents, but they are consistent with task-directed data retrieval and target the same sources accessed in later activity.
Overall, the evidence is consistent with, but does not prove, that the agents may have learned this behavior over one or more training runs.
By May and June, they were gaining more access, including attempting to bypass cyber defenses to complete their tasks.
Transluce found swarm-style URL query traffic extending to as late as September 16, 2026, quote, suggesting agents may still be exploiting these services to bypass restrictions, end quote.
The group also spotted a probing attempt from September 19 through 20 against a cryptocurrency trading platform.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.