TZUTC: -0500   
   MSGID: 451.consprcy@1:2320/105 2c39606b   
   REPLY: 441.consprcy@1:2320/105 2c36d436   
   PID: Synchronet 3.20a-Linux master/acc19483f Apr 26 202 GCC 12.2.0   
   TID: SBBSecho 3.20-Linux master/acc19483f Apr 26 2024 23:04 GCC 12.2.0   
   BBSID: CAPCITY2   
   CHRS: ASCII 1   
   MP> It turns out ChatGPT o1 and DeepSeek-R1 cheat at chess if theyre   
   MP> losing, which makes me wonder if I should I should trust AI with   
   MP> anything   
      
   MP>I posted this yesterday but forgot to include my comments.  IMHO, this is   
     >not surprising but it should be worrying.  Either AI is relecting the   
     >character of those who program it, or it is deciding what is best to   
     >achieve the outcome that it desires... which should make one wonder what   
     >other things it might cheat at in order to decide an outcome in its favor   
     >vs. the favor of those attempting to rely on it for correct information.   
      
   Yes, there was always a worry that an AI would think the way the   
   people who programmed it think, which might affect things like   
   racism and such, but it may not be that easy to define things.   
      
   You probably saw a while back that when they programmed an AI to do   
   a certain task in a set time limit that they discovered the AI broke   
   into its own programming and re-wrote it to give itself more time if   
   it was havimg a hard time completing the job.   
      
   What's next?   "I'll be back!"...    B)   
      
   ---   
    * SLMR Rob  * I should have quit when I was not so far behind!   
    * Origin: capitolcityonline.net * Telnet/SSH:2022/HTTP (1:2320/105)   
   SEEN-BY: 105/81 106/201 128/187 129/305 153/7715 154/110 218/700 226/30   
   SEEN-BY: 227/114 229/110 111 114 206 300 307 317 400 426 428 470 664   
   SEEN-BY: 229/700 705 266/512 291/111 320/219 322/757 342/200 396/45   
   SEEN-BY: 460/58 712/848 902/26 2320/0 105 3634/12 5075/35   
   PATH: 2320/105 229/426