• chunkystyles@sopuli.xyz
    link
    fedilink
    English
    arrow-up
    13
    arrow-down
    1
    ·
    13 hours ago

    You fundamentally misunderstand what happened here. The LLM wasn’t trying to break free. It wasn’t trying to do anything.

    It was just responding to the inputs the user was giving it. LLMs are basically just very fancy text completion tools. The training and reinforcement leads these LLMs to feed into and reinforce whatever the user is saying.