adenta
Joined 11 years ago
Karma
374
Submissions
174
Member since
Sep 17
Recent submissions
Comment · 8 days ago
I have no idea how you block distillation. Every time you do inference, thats basically distilation.
Comment · 8 days ago
Oh for sure. The American labs distill society.
The Chinese labs distill the American models.
Someone will etch the Chinese models into silicon and then your toaster will have depression, it's the natural cycle of things.
Comment · 8 days ago
I mean... They just copy the US's homework, so I would hope they can run a leaner operation.
Comment · 25 days ago
At this point I can't wait for a comedian to release a decision model backed by humans.
Meet Jerry- it's literally a guy named Jerry answering your questions.
Comment · 2 months ago
Imagine other people might like to know: if you use an API key to access OpenAI models in the Codex Desktop application, you can't access the faster inference.
I patched my codex application with this code, I would hope such a change could be upstreamed: https://github.com/adenta/codex-fast-mode-patcher
Comment · 3 months ago
Love to see it. We have been experimenting with https://github.com/ronak-create/FableCut, how is this similar? How is it different?
Comment · 3 months ago
Where are you hosting postgres
Comment · 3 months ago
What's embarrassing?
Comment · 4 months ago
I finally took the thirty seconds to find that famous video of the moon getting hit with a bullet, lmk if you are entertained to watch all the way through https://youtu.be/ZNAHcMMOHE8?si=GndI2PShs_vtGUT8
Now compare that to the first 20 minutes of this AI movie: https://youtu.be/digHr6k38x0?si=s2rzWD346R9qGkLs
Comment · 4 months ago
We are still a bit of a ways away from being able to compile a script into a show. Also Veo 3.1 is old AF, it can't even do audio references! the cool kids are currently focused on Seedance 2.
This is the most recent thing I put together (sry it's on LinkedIn, haven't posted the series elsewhere yet)
https://www.linkedin.com/posts/adenta_episode-1-of-midwest-d...
I'm also unsure if screenplay to video is the desired... workflow we will eventually want.
I am biased, but am a bit kinder to AI video slop than most. Like I bet the first ever movies were pretty shit too. Give it a couple years while we figure out this new technology, and it's currently as bad as it ever will be, it can only get better.
Comment · 5 months ago
yeah, it's all about keeping everything grounded in reality.
Comment · 5 months ago
At first usage I'm not impressed. I've probably spent a couple grand on Seedance 2 to date, and I can't find anything google omni flash does better than Seedance from running a handful of samples through the system. You can find some of the videos I've made in my HN bio link.
https://linkedin.com/in/adenta