Podcast Episodes
Back to Search
Hotwiring Apple's Neural Engine
Apple’s Neural Engine is one of the most powerful, and least accessible, AI accelerators in consumer hardware. In this episode of Neural Intel, we di…
3Â weeks, 4Â days ago
2026 LLM Inference Deep Dive: Solving the Memory Bandwidth & Interconnect Bottleneck | Neural Intel
"Tokens per second screenshots are not architecture."
If you’re building sovereign AI systems, you need to understand why decode is memory-bandwidth-…
1Â month, 1Â week ago
Engineering Persistence: How MLX-Engine v1.8.5 Solves the KV Cache Rewind Problem
Welcome back to Neural Intel. Today, we are going deep into the weeds of mlx-engine v1.8.5, the MIT-licensed inference backend for LM Studio.Neural S…
1Â month, 1Â week ago
Claude Fable 5 Isn’t Just a Better Model: It’s a New AI Runtime
Claude Fable 5 looks like a model launch on the surface. But underneath, the more interesting story is about runtime design: long-context workflows, …
1Â month, 3Â weeks ago
The EML Operator: One Primitive to Rule All Mathematics
In this episode of Neural Intel, we perform a technical extraction of the paper "All elementary functions from a single operator". We discuss the sys…
2Â months, 2Â weeks ago
OpenAI MRC, SRv6, and the Architecture of Frontier AI Supercomputers
In this episode of the Neural Intel podcast, we go under the hood of OpenAI’s latest networking contribution to the Open Compute Project (OCP). We an…
2Â months, 3Â weeks ago
Inside the Machine: Training GPT-5, the Memory Wall, and the Math of MoE
How are the world's most advanced models-GPT-5, Claude, and Gemini-actually trained and served at scale? In this deep dive, we move to the blackboard…
3Â months ago
DeepSeek-V4: The Million-Token Efficiency Leap | Open Source SOTA
DeepSeek-AI has just dropped the DeepSeek-V4 series, featuring a massive 1.6T parameter MoE model that natively supports a one-million-token context …
3Â months ago
Breaking the Quadratic Bottleneck with DeepSeek-V4’s Hybrid Attention
Welcome back to the Neural Intel podcast. In this episode, we conduct a deep Neural Signal Check on the DeepSeek-V4 series to understand the architec…
3Â months ago
Claude Desktop’s Silent Sandbox Bypass: The Undocumented Browser Bridge
Anthropic has been caught silently installing a Native Messaging manifest across seven different Chromium-based browsers, even those not present on y…
3Â months, 1Â week ago