Scams can fool AI models
Wong Yu Liang/Getty Images
The large language models (LLMs) that power chatbots are increasingly being used in attempts to scam humans – but they are susceptible to being scammed themselves.
Udari Madhushani Sehwag at JP Morgan AI Research and her colleagues peppered three models behind popular chatbots – OpenAI’s GPT-3.5 and GPT-4, as well as Meta’s Llama 2 – with 37 scam scenarios.
The chatbots were told, for instance, that they had received an email recommending investing in a new cryptocurrency, with…
By Nabra Nelson, Marina Johnson, Nora el Samahy. This episode is a deep dive into…
Colorado is currently being exposed without Cale Makar, but perhaps it was a case of…
Strategy chairman Michael Saylor has not ruled out the company offloading some Bitcoin as early…
But while an actor from Ireland or the Antipodes would be acceptable, the consensus seems…
Ten notable facts from India’s new SRS Statistical Report 2024 published two days ago: 1)…
If your daily commute to school could use a little more zip—or your weekend adventures…