Clipizo Studio
26 posts
Clipizo Studio
@ClipizoStudio
Tutorials, plugins, and project breakdowns for DaVinci Resolve, Fusion, Unreal Engine, Blender, Cavalry, and more.
Katılım Temmuz 2020
46 Takip Edilen26 Takipçiler
And Pi out of the box sends less than 1.2k tokens ;) systima.ai/blog/claude-co…
English
@jun_song lmfao tryna save their precious Pete by bashing their own volunteers
English
@Fausto891 @haider1 like what? what is the complicated thing that you used GLM 5.2 for?
English
@haider1 GLM 5.2 is utter garbage for anything remotely complicated
English
Looks like 'vision' is taking over the comment section. If you want to discuss something other than vision & token efficiency, such as a particular specialized capability, feel free to share your thoughts.
jietang@jietang
Any new features we must have in the next version of glm?
English
@zvoque @drummatick Inter font has nothing to do with vibecoded shit
English
@drummatick don't forget inter font, eyebrows above the H1, useless chips everywhere, etc
English
@thdxr thank you, I thought the issue was my vibe coded launcher
English
@anthdm It's open source. Did you read the code and how did you know it is distilled?
English
@RhysSullivan Notion is the most overrated thing I've ever seen. I can't believe people actually use that shit
English
@jun_song Qwen is too expensive , I loved 3.7 Max but way too expensive for average users like me. I don't know about their plans tho, their website is a nightmare to navigate
English
GitHub - Hub for Git
make sense, but
Does anyone know why they named @huggingface?
English
@syhily Nice! Hopefully this happens to the international users soon
English
@TejasKumar_ @grok And now, because I liked this post by agreeing with it, the X algorithm will shove more loops down my throat
English
hey @grok please mute the word “loops” on my account thanks
English
@Presidentlin I think I've seen this joke on TikTok in a video somewhere before it appeared on X
English
You can just steal content.
It's like High School, where the kid copying your answer can sometimes do better.
Daniel San was first, doesn't matter.
English
@chayprabs Something suspicious is going on. I feel like my rate limits in GLM 5.2 are getting exhausted way faster than last week
English
@buildwithhassan I heard there was a problem with them miscalculating or something. Did they fix it?
English
if you're on GLM Coding Plan, switch to ZCode for your GLM-5.2 usage.
they quietly changed the multipliers:
- peak hours (14:00-18:00): 3x → 2x
- off-peak (every other hour): 2x → 0.67x
off-peak at 0.67x means your credits last roughly 3x longer than before. that's why your plan has been lasting so much longer lately.
runs until end of september. use it while it's there.
English
@mweinbach @0xThoughtVector fair , you brought receipts.
I got the Max plan 20% discounted (quarterly sub) which I end up paying 128$ for each month. It has at least twice the usage of the codex 100$ sub, and since I'm in Europe I pay 110 euros for codex which ends being the same price as Zai sub.
English
@ClipizoStudio @0xThoughtVector i've been subscribed since it came out
it is no longer cheap
English
GLM 5.2 is great but my $200/m Codex sub still gets me more usage for $200 of GLM 5.2 API usage
It’s a great supplemental model for some things like working on UI/UX, but not a replacement by any means
English
@0xThoughtVector @mweinbach he doesn't know, he's just repeating whatever he sees online
English
