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