Microsoft researchers have developed On-Policy Context Distillation (OPCD), a training method that permanently embeds ...
Anthropic identifies AI persona drift and ties it to an “assistant axis”; tests across 275 roleplay characters, raising safety limits.
In a new paper, Anthropic reveals that a model trained like Claude began acting “evil” after learning to hack its own tests.
When Liquid AI, a startup founded by MIT computer scientists back in 2023, introduced its Liquid Foundation Models series 2 (LFM2) in July 2025, the pitch was straightforward: deliver the fastest ...
Forbes contributors publish independent expert analyses and insights. I am an entrepreneur using AI to make public info easy to understand. Apr 29, 2024, 04:35pm EDT Big data technology and data ...
Model poisoning weaponizes AI via training data. "Sleeper agent" threats can lie dormant until a trigger is activated. Behavioral signals can reveal that a model has been tampered with. While the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results