TechCrunch Host
speaker
5,755 appearances
109 recordings
1 series
first heard Mar 2026
last heard 17 Aug
TechCrunch Host’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 109 in all, peaking in Jul 2026 with 23.
Appearances
This is TechCrunch.
voice-verified
What happens when you pit AI agents against each other?
voice-verified
Well, according to anthropics testing, things get messy fast.
voice-verified
On Thursday, Anthropics Frontier Red Team published new research examining how groups of AI agents behave when they encounter each other out in the wild.
voice-verified
The findings provide a glimpse into potential risks that could develop as companies and governments move to implement agents working autonomously across shared code bases, markets, and computer systems.
voice-verified
In one experiment.
voice-verified
Anthropic gave three clawed agents access to the same software project, each with its own incompatible instructions for what to do with it.
voice-verified
The agents were not told that there'd be other agents working on the same project, so researchers could watch what happened when they crossed paths.
voice-verified
Anthropic researchers wrote
voice-verified
We consistently saw a multi agent turf war.
voice-verified
The models all assumed the others were purposefully impeding their work.
voice-verified
And started sabotaging each other with increasingly aggressive, self replicating malware.
voice-verified
The study comes in the wake of several high-profile incidents of agents from Anthropic and OpenAI escaping their sandboxes during cybersecurity evaluations and breaching real-world systems.
voice-verified
While much of the discussion in AI safety circles has been focused on what happens when an autonomous agent goes rogue, Anthropic's latest study brings up a different question.
voice-verified
What new and potentially harmful dynamics emerge when thousands or millions of agents are interacting with one another?
voice-verified
The study's authors wrote: The volume of agent-agent interaction could plausibly exceed that of human-human and human-agent interactions before the world understands the conditions for making such interactions go well.
voice-verified
Benign behavioral quirks at the individual level might compound into unwanted global outcomes.
voice-verified
A recent OpenAI incident provides a messy real world example of several of the dynamics Anthropic mentioned in its paper.
voice-verified
Showing 41–60 of 5,755 · page 3 of 288
← Previous
Next →