[HN Gopher] How ProPublica Uses AI in Its Investigations
       ___________________________________________________________________
        
       How ProPublica Uses AI in Its Investigations
        
       Author : marban
       Score  : 56 points
       Date   : 2025-03-14 15:19 UTC (7 hours ago)
        
 (HTM) web link (www.propublica.org)
 (TXT) w3m dump (www.propublica.org)
        
       | nsagent wrote:
       | > And crucially, we made sure to tell the model not to guess if
       | it wasn't sure. (AI models are known to hallucinate, and we
       | wanted to guard against that.)
       | 
       | Prompting an LLM not to confabulate won't actually prevent it
       | from doing so. It's so disappointing to see an organization like
       | this, that's mission is to inform the public, used AI not
       | understanding the limitations and then making a claim like this.
        
         | llamaimperative wrote:
         | It definitely does mitigate the risk (pretty substantially in
         | my experience!)
        
         | profchemai wrote:
         | Criticism feels harsh. Of course models don't know what they
         | don't know. Reporters can have the same biases. They could have
         | worded it better "lowers the probability of hallucinating", but
         | it is correct it helps to guard against it. It's just that it's
         | not a binary thing.
        
           | jgalt212 wrote:
           | > we made sure to tell the model not to guess if it wasn't
           | sure
           | 
           | Fair enough, but it's kind of ridiculous that in 2025 this
           | "hack" still helps produce more reliable results.
        
         | simonw wrote:
         | From that same article:
         | 
         | > Of course, members of our staff reviewed and confirmed every
         | detail before we published our story, and we called all the
         | named people and agencies seeking comment, which remains a
         | must-do even in the world of AI.
         | 
         | That sounds to me like they absolutely do understand the
         | limitations of the technology they are using.
        
       ___________________________________________________________________
       (page generated 2025-03-14 23:02 UTC)