alt Hacker NewsThat can occur in a cloud-based, closed-weight model as well. So this argument makes no sense.
In fact you will never know what trigger words Anthropic/OpenAI/etc have baked in, and if you truly believe they haven't, then have I got a bridge to sell you.
Replies
jstanley • today at 8:01 AM
They don't need trigger words because they can just issue whatever tool calls they want regardless of what the model itself wants to do.
iugtmkbdfil834 • today at 5:53 AM
To be fair, if you got money to burn, you can attempt to 'fuzz' either of the major US providers, but finding the right triggers won't be cheap.
linkregister • today at 4:56 AM
What is the value in making an unfalsifiable assertion?
➕ show 1 reply
That’s an argument against Anthropic/OpenAI, not for Deepseek. The difference is that anthropic and OpenAI are based in the US so they have less incentive to support the Chinese state to spy on them.