MSGID: <10gp8rt$3985n$1@dont-email.me> 0a92829c   
   REPLY:  f2a1e80d   
   PID: PyGate 1.5.1   
   TID: PyGate/Linux 1.5.1   
   CHRS: ASCII 1   
   TZUTC: 0000   
   REPLYADDR james.harris.1@gmail.com   
   REPLYTO 3:633/10 UUCP   
   On 03/12/2025 09:48, Anssi Saari wrote:   
   > James Harris  writes:   
   >    
   >> As you can see, it does say clearly that Linux can handle ECC reports   
   >> on the CM5 but thus far I've not found any sources to back it up.   
   >    
   > Why not ask your chosen AI tool to simply provide links to sources and   
   > verify yourself? With a quick search I didn't find support for any of   
   > this ECC support stuff either, except for the standard on-die ECC.   
      
   IME asking Grok to provide links is an exercise in futility. The URLs    
   look ideal - they have all the components in them that you would think    
   would answer your query - but when you click on them you get a 404 or    
   the wrong article.   
      
   Grok says it's called AI hallucination and is common to other AI    
   engines, too, and that its makers are working on fixing it in future.    
   For now, however, its links are rubbish.   
      
   So are some of its quotations.   
      
   Both problems seem to be something to do with recognising patterns and    
   generating corresponding patterns   
      
      
   --    
   James Harris   
      
      
      
   --- PyGate Linux v1.5.1   
    * Origin: Dragon's Lair, PyGate NNTP<>Fido Gate (3:633/10)   
   SEEN-BY: 105/81 106/201 128/187 129/14 305 153/7715 154/110 218/700   
   SEEN-BY: 226/30 227/114 229/110 112 134 200 206 275 300 317 400 426   
   SEEN-BY: 229/428 470 616 664 700 705 266/512 291/111 292/854 320/219   
   SEEN-BY: 322/757 342/200 396/45 460/58 633/10 280 414 418 420 422   
   SEEN-BY: 633/509 2744 712/848 770/1 902/26 2320/105 5020/400 5075/35   
   PATH: 633/10 280 229/426