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 Kristin Marting. On 6 April 2026, TORCHES continues with a conversation with the incomparable…
The Rangers’ kids are coming alive, snapping the Rangers’ six game losing streak in a…
OKX’s X Layer is the 21st blockchain to integrate Aave, which recently surpassed the $1…
Half Man premieres 23 April on HBO and HBO Max in the US and 24…
Marginal Garfield generates an original Garfield cartoon every day based on posts from Marginal Revolution!…
You can find a classroom-ready copy of our Anticipation Guide prompts here. The Great Gatsby…