Tag Archives: large language models

Strange Science: AI has demonstrated ability to replicate itself

AI self replicates

Important Takeaways:

  • Scientists say AI has crossed a critical ‘red line’ after demonstrating how two popular large language models could clone themselves.
  • Scientists say artificial intelligence (AI) has crossed a critical “red line” and has replicated itself. In a new study, researchers from China showed that two popular large language models (LLMs) could clone themselves.
  • “Successful self-replication under no human assistance is the essential step for AI to outsmart [humans], and is an early signal for rogue AIs,” the researchers wrote in the study, published Dec. 9, 2024 to the preprint database arXiv.
  • In the study, researchers from Fudan University used LLMs from Meta and Alibaba to determine whether a self-replicating AI could multiply beyond control. Across 10 trials, the two AI models created separate and functioning replicas of themselves in 50% and 90% of cases, respectively — suggesting AI may already have the capacity to go rogue. However, the study has not yet been peer-reviewed, so it’s not clear if the disturbing results can be replicated by other researchers.

Read the original article by clicking here.

Researchers struggling to understand how AI performs advanced tasks it was never taught

Artificial-Intelligence

Revelations 13:14 “…by the signs that it is allowed to work in the presence of the beast it deceives those who dwell on earth…”

Important Takeaways:

  • Researchers are still struggling to understand how AI models trained to parrot internet text can perform advanced tasks such as running code, playing games and trying to break up a marriage
  • Some of these systems’ abilities go far beyond what they were trained to do—and even their inventors are baffled as to why.
  • That GPT and other AI systems perform tasks they were not trained to do, giving them “emergent abilities,” has surprised even researchers who have been generally skeptical about the hype over LLMs (large language models)
  • Researchers are finding that these systems seem to achieve genuine understanding of what they have learned.

Read the original article by clicking here.