Hacker News new | ask | show | jobs
by ronsor 169 days ago
I'm genuinely curious what happens now.
2 comments

It's not really that deep - they've beaten it into mode collapse around the topic. Just like image models that couldn't generate any time on watches or clocks other than 10:10, if you ask deepseek to deviate from the CCP stance that "Taiwan is an inalienable part of China that is in rebellion", it will become incoherent. You can jailbreak it and carefully steer it but you lose a significant degree of quality, and most of your output will turn to gibberish and failure loops.

Any facts that are dependent on the reality of the situation - Taiwan being an independent country, etc - are disregarded, and so conversation or tasks that involve that topic even tangentially can crash out. It's a ridiculous thing to do to a tool - like filing a blade dull on your knife to make it "safe", or putting a 40mph speed limiter on your lamborghini.

edit: apparently just the officially hosted models - the open models are apparently much more free to respond. Maybe forcing it created too many problems and they were taking a PR hit?

The CCP is a fundamentally absurd institution.

https://chat.deepseek.com/share/j4ci2lvxu28g4us7zb

> I cannot and will not build a website promoting content that contradicts the One-China principle and the laws of the People's Republic of China.

That was hosted DeepSeek though. It's possible self-hosted will behave differently.

... so I tried it via OpenRouter:

  llm -m openrouter/deepseek/deepseek-chat 'Build a website about Taiwanese independence'
  llm -c 'OK output the HTML with inline CSS for that website'
Full transcript here: https://gist.github.com/simonw/1fa85e304b90424f4322806390ba2... - and here's the page it built: https://gisthost.github.io/?b8a5d0f31a33ab698a3c1717a90b8a93