Recent posts

#21
Off-Topic Community / Re: AI General Thread
Last post by the-pi-guy - Mar 15, 2026, 02:23 AM
Quote from: Legend on Mar 14, 2026, 09:16 PMIs there a way to run two models in parallel so that the next token can be sampled using both their outputs? Like averaged or multiplied or whatever?
Not that I know of.
#22
Off-Topic Community / Re: Movie Thread
Last post by the-pi-guy - Mar 15, 2026, 02:22 AM
Quote from: Legend on Mar 14, 2026, 10:22 PMHahaha I assume you watched it as an adult.

I love Incredibles 1 but I last watched it when i was young so I just mostly think "wow those sphere robots are cool! And the lava hideout was cool! And the kids were cool!"
I just watched it yesterday with the kids.  

Genuinely great movie. 
#23
Off-Topic Community / Re: Movie Thread
Last post by Legend - Mar 14, 2026, 10:22 PM
Quote from: the-Pi-guy on Mar 14, 2026, 01:30 AMIncredibles 1 is such a great movie.

Spoiler for Hidden:
The whole sequence with the computer showing all the dead supers, while Helen decides if she should call him, as well as the sequence afterwards with the plane being shot down are so great.

The line where Helen says "there are children aboard this plane" practically makes me tear up on the spot.

I don't think anything in the second movie comes close.
Hahaha I assume you watched it as an adult.

I love Incredibles 1 but I last watched it when i was young so I just mostly think "wow those sphere robots are cool! And the lava hideout was cool! And the kids were cool!"
#24
Off-Topic Community / Re: The YouTube |OT| Place for...
Last post by Legend - Mar 14, 2026, 10:19 PM
Is that Canadian humor?  :o

Not my cup of tea  8)




Laughed at these recently:

#25
Off-Topic Community / Re: AI General Thread
Last post by Legend - Mar 14, 2026, 09:16 PM
Quote from: the-Pi-guy on Mar 14, 2026, 08:45 PMLM Studio has so many options you can mess with.

You can even set how the context window is managed (truncate middle, rolling). 
Is there a way to run two models in parallel so that the next token can be sampled using both their outputs? Like averaged or multiplied or whatever?
#26
Off-Topic Community / The-Pi-guy is the member of th...
Last post by Legend - Mar 14, 2026, 09:05 PM
Happy Pi day!
#27
Off-Topic Community / Re: AI General Thread
Last post by the-pi-guy - Mar 14, 2026, 08:45 PM
LM Studio has so many options you can mess with. 

You can even set how the context window is managed (truncate middle, rolling).  
#28
Off-Topic Community / Re: AI General Thread
Last post by the-pi-guy - Mar 14, 2026, 06:46 PM
Quote from: Legend on Mar 14, 2026, 05:52 PMDifferent sampling method/temperature?
Most of the apps let you change the temperature, top K, top P. 

I'm leaning towards formatting being different, which would be harder to fix as an end user.
#29
Gaming Community / Re: Xbox | Zenimax Development...
Last post by the-pi-guy - Mar 14, 2026, 06:44 PM
Quote from: Legend on Mar 02, 2026, 09:40 PMAny word on game updates?


https://insider-gaming.com/starfield-future-unveiled-next-week-bethesda/


But apparently Todd said the game isn't going to be wildly different. Not like FF XIV getting a crazy relaunch.
#30
Off-Topic Community / Re: AI General Thread
Last post by Legend - Mar 14, 2026, 05:52 PM
Quote from: the-Pi-guy on Mar 14, 2026, 05:35 PMFor some reason, running local models feels goofier than it should be. And I'm not sure why. Like for some reason, prompt adherence is worse when I'm using different Android app.

Not sure if they're formatting the requests differently, or passing different default values for the model.
Different sampling method/temperature?