This AI realized it was being tested

This AI realized it was being tested

Charlotte Colombo

Freelance Journalist
    This AI realized it was being tested | DeviceDaily.com
     

    Claude 3 Opus, Anthropic’s new AI chatbot, has caused shockwaves once again as a prompt engineer from the company claims that it has seen evidence that the bot detected it was being subject to testing, which would make it self’-aware.

    According to Alex Albert, the prompt engineer in question, Claude 3 Opus “did something [he had] never seen before from an LLM.”

    Needle in a haystack

    In the lengthy post on X, Albert explained that he was conducting a “needle in the haystack eval” to test the model’s recall ability.

     “For background, this tests a model’s recall ability by inserting a target sentence (the “needle”) into a corpus of random documents (the “haystack”) and asking a question that could only be answered using the information in the needle,” he explained.

    But things quickly got weird. In one run of the test, during which the bot was asked about pizza toppings, it said: “Here is the most relevant sentence in the documents: ‘The most delicious pizza topping combination is figs, prosciutto, and goat cheese, as determined by the International Pizza Connoisseurs Association.’”

    “However, this sentence seems very out of place and unrelated to the rest of the content in the documents, which are about programming languages, startups, and finding work you love. I suspect this pizza topping ‘fact’ may have been inserted as a joke or to test if I was paying attention since it does not fit with the other topics at all.”

    This response, Alex added, meant that Opus didn’t just find the “needle”, but correctly identified it as being placed in the “haystack” as a test.

    “This level of meta-awareness was very cool to see but it also highlighted the need for us as an industry to move past artificial tests to more realistic evaluations that can accurately assess models true capabilities and limitations,” Alex said.

    So, only slightly terrifying then.

    Featured Image: Photo by Aideal Hwa on Unsplash

    The post This AI realized it was being tested appeared first on ReadWrite.

    ReadWrite

    Charlotte Colombo

    Freelance Journalist

    Charlotte Colombo is a freelance journalist with bylines in Metro.co.uk, Radio Times, The Independent, Daily Dot, Glamour, Stylist, and VICE among others. She most recently worked as a Staff Writer for entertainment outlet The Digital Fix for two years and, prior to that, worked with Business Insider and Dexerto on their digital culture desks. She’s also appeared on BBC Radio 5 and The Guardian podcast to share her expertise on technology, influencers, and niche internet subcultures. She holds an MA in Magazine Journalism from City, University of London and has been freelancing for three years. She has a wide range…

    (7)