[HN Gopher] How RLHF Preference Model Tuning Works (and How Thin...
       ___________________________________________________________________
        
       How RLHF Preference Model Tuning Works (and How Things May Go
       Wrong)
        
       Author : dylanbfox
       Score  : 87 points
       Date   : 2023-08-09 12:33 UTC (10 hours ago)
        
 (HTM) web link (www.assemblyai.com)
 (TXT) w3m dump (www.assemblyai.com)
        
       | lyapunova wrote:
       | No disrespect. This article isn't terrible (and I did learn
       | something practical), but isn't the underlying purpose of this
       | post to advertise whatever service assemblyai.com provides?
       | 
       | Why is it necessary for MLOps product websites to have blogs?
       | This content could also be posted on Medium or the author's
       | personal project website and serve the same purpose (arguably
       | helping the author's brand more effectively). The only downside
       | would be that this startup would not get the indirect
       | advertising.
        
         | smaddox wrote:
         | Startups often blogs in order to increase their visibility. It
         | can help with both marketing and recruiting.
        
       | Valgrim wrote:
       | Is there any chat app which puts the user to contribution by
       | generating two parallel answers side by side, and the user
       | chooses which one it wants to respond to?
        
         | esafak wrote:
         | Bard's "View other drafts".
        
       ___________________________________________________________________
       (page generated 2023-08-09 23:01 UTC)