Alexander Derve

I'm not a computer genius, but I'm pretty good at googling things.

[Alexander Derve @AlexanderDerve]

@AISafetyMemes amazing

[Alexander Derve @AlexanderDerve]

@burkov Pretty insightful, I also think a lot of RL training is focused on straight forward tasks where there is a defined problem and solution. Meanwhile a lot of these real world tasks involve a ton of unknowns/required trial and error, and this process goes well outside the training.

[Michael Antonelli @BullandBaird]

No bigger lie

[Alexander Derve @AlexanderDerve]

@AskPerplexity Can confirm, my day was ruined

[Alexander Derve @AlexanderDerve]

@NousResearch Why use Llama for the base?

[Alexander Derve @AlexanderDerve]

@cuemewch If you have central AC but aren't getting enough cold air in your room I'd try out a register booster, they work pretty alright.

https://t.co/2jMlIXOHAN

[💗 Lunie 💗 @Back2Batk]

AI voices will never surpass the power of sentence mixing

[non aesthetic things @PicturesFoIder]

If the keyboard button was a person

[Alexander Derve @AlexanderDerve]

@cocktailpeanut @deepbeepmeep @TXhunyuan Any preference between wan2.1 and HunyuanVideo?

[Massimo @Rainmaker1973]

The little joy of this dog who figured out how to have fun on an escalator.
https://t.co/5qF0SZbQ5J

[Qwen @Alibaba_Qwen]

Today, we release QwQ-32B, our new reasoning model with only 32 billion parameters that rivals cutting-edge reasoning model, e.g., DeepSeek-R1.

Blog: https://t.co/jpNEx0Ck8p
HF: https://t.co/h91przQmoP
ModelScope: https://t.co/p0ztmZpWIZ
Demo: https://t.co/sxVVRFwunC
Qwen Chat: https://t.co/bg4tAU1p74

This time, we investigate recipes for scaling RL and have achieved some impressive results based on our Qwen2.5-32B. We find that RL training con continuously improve the performance especially in math and coding, and we observe that the continous scaling of RL can help a medium-size model achieve competitieve performance against gigantic MoE model. Feel free to chat with our new models and provide us feedback!

[Alexander Derve @AlexanderDerve]

@techspence This is like a gamified next level tabletop exercise, absolutely love it. Is there a campaign pdf or rule set for this?

[Alexander Derve @AlexanderDerve]

@cocktailpeanut @deepbeepmeep @Alibaba_Wan Is this also faster than the default comfy UI workflow?

[Alexander Derve @AlexanderDerve]

@amazon When is this coming to Canada?

[Alexander Derve @AlexanderDerve]

@SecurityAura Yup, anything over 24 hours takes forever to load if it even works at all, fortunately you can just query them from log analytics

[Alexander Derve @AlexanderDerve]

@teknium If you pay OpenAI $200 a month you deserve nothing

[Alexander Derve @AlexanderDerve]

@Alibaba_Wan This is 🔥
Any sample videos from the 1.3B model?

[Alexander Derve @AlexanderDerve]

@VikParuchuri Would love to see this on newspapers, comics/manga and magazines.

[Alexander Derve @AlexanderDerve]

@carrigmat Any good 8 slot DDR5 motherboards/cpu combos that are cheaper? 24 channel seems excessive. I'd be happy running it at Q4.