sub:assertion {
<
https://sharelm.github.io/> <
https://sense-nets.xyz/hasZoteroItemType> "webpage" .
sub:assertion dcterms:creator <
https://w3id.org/np/RAoSadUw99CeqDlR2400018nqTzR_38fT86OrTzk16Vts> ;
<
http://purl.org/spar/cito/includesQuotationFrom> <
https://x.com/LChoshen/status/1813662203532263467> ;
rdfs:comment """ I just had the most marvelous chat with @CohereForAI-R, Claude and Latex (next tweet)
I asked +R to explain a latex error, and it failed.
NP, happens
Claude gave a partial direction, sending me back to latex
In latex I found the error, but was too lazy to solve
so ...
1/2 https://twitter.com/LChoshen/status/1817455710365495492/photo/1
I gave Claude the additional feedback and it
Solved it!
Then came the surprising moment
In parallel, I also told R about my discussions with Claude, and it recognized the feedback perfectly!
If only I could improve models that way...
(data is collected by https://sharelm.github.io/) https://twitter.com/LChoshen/status/1817455713054077372/photo/1
So maybe natural feedback extraction would be able to use it one day?
https://x.com/LChoshen/status/1813662203532263467
P.S. Think if we didn't only save chats and feedback and extracted, but UIs would have asked:
I noticed you had a problem, was it solved eventually? How?
Like stack overflow for our own (open, mind you) specialized models.
I'd be happy to teach them if it was used to help others
""" ;
<
https://sense-nets.xyz/announcesResource> <
https://sharelm.github.io/> ;
<
https://sense-nets.xyz/endorses> <
https://x.com/Shachar_Don/status/1813578072593150137> .
<
https://x.com/LChoshen/status/1813662203532263467> <
https://sense-nets.xyz/hasZoteroItemType> "forumPost" .
<
https://x.com/Shachar_Don/status/1813578072593150137> <
https://sense-nets.xyz/hasZoteroItemType> "forumPost" .
}