gmale

fiat lux. go bears.

[gmale @LaptopCrust]

@ChaoticEclipse0 @0xocdsec What’s stopping you from going out there and living a normal life?

[gmale @LaptopCrust]

@hungtran @eastdakota Nice try, bot

[gmale @LaptopCrust]

@limitlesstack How do you get rid of the headaches and crazy insomnia?

[gmale @LaptopCrust]

@Dipper_pol With the exception of life and death situations, there are few scenarios where you have 70/30 split of a highly positive outcome that you should avoid.

[Sudo su @sudoingX]

this guy has 29 models on huggingface at page 2 ranking. no lab behind him. no sponsorship. $2,000 from his own pocket on GPU rentals. he compressed GLM-4.7 to run on a MacBook and quantized Nemotron Super the week it dropped. all public. all free.

nvidia is a trillion dollar company with hundreds of teams but they are not the ones quantizing models middle of the night and pushing them out before sunrise. if nvidia stopped tomorrow their employees stop working. people like @0xSero would not. that is the difference between a paycheck and a mission.

@NVIDIAAI you talk about making AI accessible. the people actually doing it are right here. 29 models deep burning their own compute with no ask except more hardware to keep going. you do not need to build another program. just look at who is already building for you. one GPU to this man would produce more public value than a hundred internal sprints.

i am not asking for charity. i am asking you to invest in someone who already proved it.

[gmale @LaptopCrust]

@chrysb @openclaw does this work with existing installs?

[gmale @LaptopCrust]

@0xSero Have a cluster with 96GB RAM, any use in that?

[gmale @LaptopCrust]

@max_paperclips @Orwelian84 what are your use cases for qwen 9b? I’m finally getting around to wiring up my home lab and want to have it doing something at all hours of the night, could use some inspiration

[gmale @LaptopCrust]

@JustinLin610 🐐

[gmale @LaptopCrust]

@thestanduppod @DefNotZap you buy a stack of these and wire them up through thunderbolt with EXO pooling your unified memory so you can run local models + spool up N instances of MacOS on a compute cluster.

[gmale @LaptopCrust]

@0xSero I’ve fallen back to old reliable iTerm

[gmale @LaptopCrust]

@repligate @deepfates wish I was there to attend. bless you for organizing this.

[gmale @LaptopCrust]

@ziwenxu_ openclaw

[gmale @LaptopCrust]

@futbalmadeeasy @WhiteHouse Anthropic assisted with the assault/capture of Maduro with claude. Results were good, Fed wants to use Claude for bigger military excursions + spying on Americans. Dario is against this, rightfully so. Good on him.

[gmale @LaptopCrust]

@0xSero interested in picking your brain about your setup. going to drop some money into credits on Parchi for a project I had in mind. mind if I DM you?

[gmale @LaptopCrust]

@zaimiri if you’re contractually obliged to keep things in house for security reasons then sure

[gmale @LaptopCrust]

@zaimiri this works when you’re hand holding agents on simple tasks but the moment you’re doing serious work the cost/time trade off is just not worth it. I’ve got 128gb of VRAM on hand and nothings competing with Opus 4.6. This is with the infra cost being 4 years of Claude Code, too.

[gmale @LaptopCrust]

@DarkBing2 @mollycantillon @max_creating pretty sure it’s https://t.co/mTaJ8WhgLf

[gmale @LaptopCrust]

@bensmithlive made my sleep quality awful and gave me really bad headaches and brain fog

[gmale @LaptopCrust]

@D_McMillan76 @steipete lol