Cixa(🇮🇳/acc)

i turn code into coffee

[Naval @naval]

Pay the world whatever it takes to leave you alone to think.

[gaurav @gaxrav]

politicians simplify complex truths to misguide.
academics complicate simple truths to guide.

one succeeds, the other confuses.

[Elon Musk @elonmusk]

Extinctionists want a holocaust for all of humanity

[Cixa(🇮🇳/acc) @Galactron71]

@idkshabnam let's meet there!

[AK @_akhaliq]

Tencent presents GameGen-O

Open-world Video Game Generation

We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

[Cixa(🇮🇳/acc) @Galactron71]

@anshstwt thanks now I won't buy it

[‎Wojak Codes @wojakcodes]

You can buy access to an idol, not to God

[sphinx @protosphinx]

new news cycle is up. new model. more compute = magic for 8-12 weeks. then back to ‘is it me or is gpt really dumb now’

sam figured it out. it’s all compute. so he went straight for his own silicon to bypass nvidia. smart move. hard to execute.

musk figured it out. went straight for compute. bought a gazillion h100s.

market knows this too. hence nvidia etc.

welcome to another hype cycle. problem is more usage is paradoxically bad.

more usage = less compute. so enjoy the magic as it dissipates slowly. 8-12 weeks of ❤️

[Cixa(🇮🇳/acc) @Galactron71]

@Sidhanth_here relatable af

[Cixa(🇮🇳/acc) @Galactron71]

@Sidhanth_here coming for breakpoint or token2049?

[Brett Hall @ToKTeacher]

@Grimezsz The “woke mind virus” is a poor description of a deeper problem: bad ideas about reason causing people to behave in fashionably irrational ways. Some are “anti-rational memes” and are often difficult to identify, as they disable the holder’s own capacity to even notice them.

[Naval @naval]

The real tax is society forcing otherwise productive people to pay attention to politics.

[Cixa(🇮🇳/acc) @Galactron71]

@thegenesisbl0ck man that looks amazing

[Marusha @maruushae]

Real

[Cixa(🇮🇳/acc) @Galactron71]

@not_ur_siri what more to lose?

[Cixa(🇮🇳/acc) @Galactron71]

@cneuralnetwork first one is god

[Cixa(🇮🇳/acc) @Galactron71]

@runtimeError952 @piyushhhxyz make my ITC stock go up!!

[kash @kashdhanda]

how to network at conferences (without feeling gross):