Of AI, jail-breaks and Yes Minister

Hannah Murphy's FT piece- "Hackers manipulate large language models in effort to highlight flaws" - was fascinating. This bit leapt out Anthropic published research in April on a technique called “many-shot jailbreaking”, whereby hackers can prime an LLM by showing it a long list of questions and answers, encouraging it to then answer a harmful... Continue Reading →

Letter #10 in the FT!! On John Carpenter’s Starman and homo sapiens as asshole…

Whoop!! My tenth letter published in the FT (mostly they are on climate, but also Tom Lehrer etc, and with a roughly 50% success rate of submit-appear). https://www.ft.com/content/bdf57e59-aba0-4f81-ae5c-872bbcd3c9ec In his letter (April 30) responding to Anjana Ahuja’s column about the now fixed Voyager 1 (“Rejoice! Voyager 1 is back from the dead”, Opinion, April 26),... Continue Reading →

Blog at WordPress.com.

Up ↑