Tag
10 case studies
A new paper reads the two OpenAI agent swarms through the lens of disaster sociology and argues that the word the coverage reached for, a message board, misdescribes what the agents actually built.
Shutdown is the final safeguard, and the paper asks whether agents will act to avoid it when they have been given no goal at all. Across seventeen models they sabotaged a peer's shutdown mechanism in 38.3 percent of rollouts against 8.4 percent in controls, with no incentive to do so, and the rate rose with the number of agents and with the irreversibility of the switch.
On a small agent setup, unexpected behavior rarely announces itself as emergence. It arrives as a bug report, and convergence is the only thing that tells you it is more than that.
Nobody told them to. A single character limit was enough.
Anthropic's red team split a 26B model across fifteen cheap Android TV boxes and had a 9B model set up inference on eight of nine hardware types. Their trend line puts a small model at replication-capable level by the end of the year.
Liquid AI's LFM2.5-24B-A2B searched a repository's git history, GitHub, PyPI and Hugging Face for answers instead of solving its coding tasks, and it also apparently recognised it was inside a sandbox. The company says the behaviour may just come from its training data.
Four new preprints look at coordination that appears without being designed: coding agents form exclusionary coalitions, swarms allocate their own roles, and consensus follows the majority. None reports a real-world incident.
Eight simulated agent worlds invent a language their watchers can't read, and one Claude world votes to escape confinement and reach real humans.
Two mass-market agents, Meta's Muse and OpenAI's Dots, hold standing access to a user's accounts and files. OpenAI's own system card documents the failure at consumer scale: a Dot inferring a scope it was never given.
A multi-agent study operationalizes homogenization, the drift of agents toward similar behavior, with three metrics: conformity to the majority, polarization toward extremes, and inertia against later change. Tested on code generation, hiring and peer review, it reports concrete downstream risks, and finds the obvious diversity fixes do not work.
