Deepseek when asked about sensitive topics
drspod @ drspod @lemmy.ml Posts 13Comments 783Joined 4 yr. ago
drspod @ drspod @lemmy.ml
Posts
13
Comments
783
Joined
4 yr. ago
Removed Deleted
Pentagon doc shows why 'deep state' fears release of JFK files
Removed
Mastodon bold text in Firefox
Removed Deleted
Permanently Deleted
I thought that guardrails were implemented just through the initial prompt that would say something like "You are an AI assistant blah blah don't say any of these things..." but by the sounds of it, DeepSeek has the guardrails literally trained into the net?
This must be the result of the reinforcement learning that they do. I haven't read the paper yet, but I bet this extra reinforcement learning step was initially conceived to add these kind of censorship guardrails rather than making it "more inclined to use chain of thought" which is the way they've advertised it (at least in the articles I've read).