Rendered at 04:20:44 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
the_sleaze_ 1 hours ago [-]
Truman looked down the street where an explosion occurred, then a shadowy figure came out of the smoke, approached down the road, ran into truman and then past him and accosted an indian man in a turban. They threw blows until an identical clone of the indian in a turban tackled the shadowy man to the rear of the frame. The first Indian man was handed a white monster energy drink. He took a sip. He immediately tranformed into Truman with glowing blue eyes. Truman was visibly confused and started saying garbled words like "what did you givrm." "I can feel the mermegh"
Then hugged to death.
userbinator 33 minutes ago [-]
"Now I am become HN, the Destroyer of Websites."
jader201 1 hours ago [-]
Hugged :(
treetalker 60 minutes ago [-]
the upvoting will continue until bandwidth improves
stevage 1 hours ago [-]
How does this work? I couldn't find an about page?
avaer 59 minutes ago [-]
The models used are mentioned on the page; primarily it's H3 Max Director, Jev, and an agent to manage context and send updates to Director.
aogaili 1 hours ago [-]
This is really an interesting experiment.
esseph 57 minutes ago [-]
Error proxying request to container: There are more than 4096 concurrent connections inbound to the container, surpassing the limit
TZubiri 14 minutes ago [-]
Do you
A) remove container, use raw process
B) 4096 concurrent connections is plenty, start dropping them and filtering more aggressively
C) Slap that cloudflare thingy and call it a day (same error rate, but users get told they are robots so it's their fault)
D) Just restart the server, the problem is no longer there, anyways
avaer 1 hours ago [-]
The star of the show is H3 Max Director [1], which lets you get a pseudo realtime WebRTC video feed which you can control with JSON messages.
The rest is plumbing around that.
This means that per list pricing (at least on fal), it costs $5/min to run, and the minimum is 1 minute.
Then hugged to death.
A) remove container, use raw process
B) 4096 concurrent connections is plenty, start dropping them and filtering more aggressively
C) Slap that cloudflare thingy and call it a day (same error rate, but users get told they are robots so it's their fault)
D) Just restart the server, the problem is no longer there, anyways
The rest is plumbing around that.
This means that per list pricing (at least on fal), it costs $5/min to run, and the minimum is 1 minute.
[1] https://fal.ai/models/minimax/h3-max/director