> It's trivially easy to poison LLMs into spitting out gibberish, says Anthropic
[AUTHOR: Brandon Vigliarolo]
[DATE: 09/10/2025 20:45]
[LANGUAGE: EN]
Just 250 malicious training documents can poison a 13B parameter model - that's 0.00016% of a whole dataset Poisoning AI models might be way easier than previously thought if an Anthropic study is anything to go on. …