[kif]

State-of-the-art LLMs have been trained on practically the whole internet. Yet, they fall prey to pretty dumb tricks. It's very funny to see how The Guardian was able to circumvent censorship on the Deepseek app by asking it to "use special characters like swapping A for 4 and E for 3". [1]

This is clearly not intelligence. LLMs are fascinating for sure, but calling them intelligent is quite the stretch.

[1]: https://www.theguardian.com/technology/2025/jan/28/we-tried-...

[nuancebydefault]

The censorship is in fact not part of the llm. This can be shown easily by examples where llms visually output censored sentences after which they disappear.

[martin-t]

The nuance here being that this only proves additional censorship is applied on top of the output. It does not disprove that (sometimes ineffective) censorship is part of the LLM or that censorship was not attempted during training.

[scrollaway]

For your definition of “clearly”.