In this episode, @latkins (CTO, Arcee AI) and @stochasticchasm (Pre-Training Lead, Arcee AI) join us to discuss the story of Trinity models and everything frontier. I can say, this talk has been one of the most amazing and technical conversations we’ve had on Ground Zero.
Check out the X Post!
Timestamp:
0:00:00 - Intro
0:00:59 - Varun’s transition from SWE to Pre-Training Lead
0:04:20 - Trinity Manifesto, Openclaw Ecosystem 0:12:15 - Arcee’s Post-Training to Pre-Training Pivot 0:23:45 - Varun’s first Pre-Training run (you can just do things!)
0:27:33 - Saturation in Pre-Training?, Mid-Training 0:37:00 - Tweaking the Training Architecture, Adam vs Muon, Evals
01:09:07 - Inference Engineering, Quick Fire, Post-Training Recipe
01:18:02 - Alpha in RL Envs, Harness Design
01:23:00 - American Open Source is trailing Chinese Competitors, Trinity Adoption
01:29:25 - Hiring at Arcee, Advice to 20yo
Watch on YouTube:
@huzzle_labs has been sponsor for this podcast. Huzzle Labs is engineering and research company focused on RL environments - mainly code, computer use, and long-horizon enterprise workflows.
So if you work in this space, research or human data, check them out!
To sponsor future episodes, visit groundzeroai.in/partner
