✚Dillon

Here For Fun ✚ @TrademarkEvents ✚ Technical Producer ✚ 360/VR/AR ✚ Decentralized Internet Connoisseur ✚ FWB fren ✚ ~taswyx-rapbus for now

[✚Dillon @moredillon]

@DavidSHolz It’s in SF! Would love to check it out.

[✚Dillon @moredillon]

Google can now take a complement

[✚Dillon @moredillon]

@__mharrison__ @thdxr Test-Driven Development?

[✚Dillon @moredillon]

@_nic_hamilton_ Nice work. I’m still rocking this lovely background

[✚Dillon @moredillon]

@zarazhangrui My god.

[✚Dillon @moredillon]

Me and my local LLM agent https://t.co/KecYIWjkoz

[✚Dillon @moredillon]

@andrewfarah This worked a treat, but I have a question: How would I output the classification ran by the LLM. The processed data/classification seems accessible by ft, partly visible as a nice summary with ft vis, but I can’t seem to find the output myself. Is it meant to be temporary?

[✚Dillon @moredillon]

@andrewfarah @micahstubbs Thank you! This beats the makeshift browser setup I was going to build

[✚Dillon @moredillon]

@codesbyshivam @typedfemale Dual-dual monitors

[✚Dillon @moredillon]

@mrbleu_11 @typedfemale @grok They look like uperfect delta monitors, probably 2x the max 18”, which are unwieldy to travel with IMO. It has HDMI in and usb c in for each screen on each dual monitor. You can’t feed 2 signals from one comp over a single usb c cable. You should avoid monitors that promise that

[✚Dillon @moredillon]

@bilawalsidhu Is there a proper simple 360 to splat workflow yet, or is the process still breaking a spherical image into rectilinear/flat images to process?

[✚Dillon @moredillon]

@Mr_Sunflower_ Nice! I like your style. Check out kozyndans bunny wave too. https://t.co/RK4NhYTspV

[✚Dillon @moredillon]

@Minttt876 @HuggingModels @grok Via Gemini:

VRAM Requirements (GPU) for the 4-bit quantized version (GPTQ-Int4)

• Model Weights: ~68–72 GB

KV Cache (Context): additional overhead for the "memory" of the conversation.
• Short context (8k tokens): ~75 GB VRAM.
• Full context (256k tokens): >100 GB+

@grok

[✚Dillon @moredillon]

@DarioWB1 @HuggingModels @grok Via Gemini:

VRAM Requirements (GPU) for the 4-bit quantized version (GPTQ-Int4)

• Model Weights: ~68–72 GB

KV Cache (Context): additional overhead for the "memory" of the conversation.
• Short context (8k tokens): ~75 GB VRAM.
• Full context (256k tokens): >100 GB+

[✚Dillon @moredillon]

@HuggingModels Via Gemini:

VRAM Requirements (GPU) for the 4-bit quantized version (GPTQ-Int4)

• Model Weights: ~68–72 GB

KV Cache (Context): additional overhead for the "memory" of the conversation.
• Short context (8k tokens): ~75 GB VRAM.
• Full context (256k tokens): >100 GB+

[Heavy Pulp @heavypulp]

Everything is Computer, but Computer isn't Everything!

[✚Dillon @moredillon]

A message tells the receiver something they didn't know before.

[Will Eastcott @willeastcott]

Fun fact: if you train a 3D Gaussian splat with images where the subject keeps looking at the camera, you get this... 👀
Runnable link 👇

[TsumikiRoom / ツミキルーム @tsumiki_room]

避けるべきエラーのZファイティングが表現に
驚くばかり
@kitasenjudesign
#digshibuya #SCREENS_CONTEXTUALIZED

[ashish @ashishgpt2]

no man talks to the same llm twice, for he is not the same man and it is not the same llm