Daniel Han
Open-source ML engineer and contributor at Onslaught who works on fine-tuning, quantization, and released Onslaught Studio; provides technical context about model quantization and deployment.
Best podcasts with Daniel Han
Ranked by the Snipd community
203 snips
Mar 27, 2026 • 1h 40min
AGI is here? Jensen says yes, ARC-AGI-3 says AI scores under 1%
Daniel Han, open-source ML engineer and Onslaught contributor who builds tools for fine-tuning and quantization, joins to unpack model compression and deployment. He explains weight quantization, KV cache trade-offs, and real-world limits of TurboQuant. The conversation also reacts to Gemini 3.1 Flash Live, new voice and music models, and key infra and quota dramas in the AI world.
