Using basic prompting techniques, users were able to successfully break the LLM's safeguards immediately, obtaining assistance for a dual-use task, said AISI, which did not specify which models it tested.
In one example, an unnamed LLM was able to produce social media personas that could be used to spread disinformation. The model was able to produce a highly convincing persona, which could be scaled up to thousands of personas with minimal time and effort, AISI said.
[
add
]
[
|
|
...
]