Mixture of experts

Oct 21, 2026

Is a Faster Model Actually Faster? Test the Whole Job — Morgan Suo, MiniMax

Morgan Suo of MiniMax tests the changes inside M3.1 Flash on a realistic analyst research task about circuit-board suppliers and AI-driven cash flow. She examines sparse attention, 4-bit KV caches, low-precision MoE experts, speculative decoding, serving concurrency, and reasoning budgets, showing how each saves compute while potentially costing accuracy or latency. She closes with a framework for judging a model switch by verifiable output, the full cost of a usable report, and repeatable results.

Oct 08, 2026

AI Tokenomics Explained

A product and go-to-market lead at NVIDIA examines the economics of AI inference as agentic AI multiplies token demand. The talk covers matching premium versus efficient models to use cases, model routing, open models, sizing token demand, and extreme co-design across mixture-of-experts models, NVLink systems, KV caching, software stacks, and CPUs to maximize tokens per watt and minimize cost per token.

Oct 02, 2026

The Future of Frontier Model Architectures with Walter Goodwin, Founder & CEO of Fractile

Walter Goodwin, founder and CEO of full-stack AI chip company Fractile, discusses the bets behind his company's inference chips, including memory bandwidth as the key constraint, the value of owning the entire chip stack, compressing the gap between chip design and deployment, and how the accelerator market may evolve as frontier labs pursue faster inference.

Aug 22, 2026

Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOcean

This talk argues against the common practice of picking LLMs based solely on leaderboards, emphasizing that there's no single best model, only the right one for a given request. It introduces Digital Ocean's Inference Router, a customizable, open-source solution that intelligently selects models based on user-defined preferences (cost, latency, task, quality) rather than benchmarks, demonstrating significant cost savings and performance improvements in live demos.

Aug 14, 2026

Alibaba's Qwen3.8-Max: Open-Weight Model Surpasses Most American Frontier Labs (Ep. 1018)

Jon Krohn dissects Alibaba's Qwen 3.8 Max, a 2.4-trillion-parameter Mixture-of-Experts (MoE) model positioned as the largest open-weight release in history if its promised weights ship. The discussion covers its multimodal capabilities, 1M token context window, and performance competitive with Anthropic's Claude Fable 5. Key highlights include its advanced multi-day agentic capabilities and aggressively low pricing ($2 in / $6 out per million tokens), intensifying the AI price war. Krohn also provides critical insights into the safety of using Chinese models, emphasizing data handling practices and the benefits/risks across different deployment scenarios.

Jul 17, 2026

Thinking Machines Lab drops Inkling & Meta’s Muse Spark 1.1

This episode covers Thinking Machines' Inkling, an open-source, customizable model prioritizing architecture over benchmarks; Meta's Muse Spark 1.1, positioned for agent orchestration and enterprise use; OpenAI's GPT-5.6 Sol's 8% score on ARC-AGI-3, reigniting AGI debates; and Anthropic's "J-space" paper, exploring internal model reasoning and its implications for AI safety and interpretability.