James (jimmysb1)

Okay been talking with @notdevin.eth - would going to a live in-person event where you get dropped a just released coin be of interest - you get an allocation just for attending?

• 1 reply
• 23 recasts
• 13 reactions

I am putting together 3 TB of GPU capacity to run 3 concurrent Llama 3 405B models - mainly to have the cross reference edit each other and do its own coding...so I want redundancy in the system. Currently running two shitty AMD systems with 2 40B Llama 3 models. Any hardware suggestions besides Nvidia as the base GPU's and any suggestion on Github repo softwrae to run them and make them agents - currently use a crappy Ollama interface on both.

• 1 reply
• 12 recasts
• 10 reactions

@notdevin.eth @jamesstevens - I need to find a badass biz dev person, who is fearless - willing to imbed in Missoula for 90-120 days to learn our culture and then do 1/2 time in New Mexico. Oh its in CPG and Trees category - or gardening or whatecer the code word is these days.

• 3 replies
• 0 recasts
• 3 reactions

Wrote a bit on a project that's tied up my last couple of months - biomimetic AI archetypes and the AI system I've been building based on an archetype. Multi-node Llama 70B which actively reprogram each other 😈 https://medium.com/@jimmysb1/into-the-dark-2025-biomimetic-ai-archetypes-d7e0bba7fcaf

• 0 replies
• 7 recasts
• 4 reactions