TZUTC: -0500   
   MSGID: 441.consprcy@1:2320/105 2c36d436   
   REPLY: 428.consprcy@1:2320/105 2c357671   
   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   
   -=> Mike Powell wrote to All <=-   
      
    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>  - Research ers have found that AI will cheat to win at chess   
    MP>  - Deep reasoning models are more active cheaters   
    MP>  - Some models simply rewrote the board in their favor   
      
    MP> In a move that will perhaps surprise nobody, especially those people   
    MP> who are already suspicious of AI, researchers have found that the   
    MP> latest AI deep research models will start to cheat at chess if they   
    MP> find theyre being outplayed.   
      
   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.   
      
   Mike   
      
      
   ... The seminar on Time Travel will be held two weeks ago.   
   --- MultiMail/DOS v0.52   
    * 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