AI Core

Fundamentals of AI models, architecture, and how they work

221 episodes · Page 4 of 10

#2357: Microsoft's Phi: When Data Quality Beats Model Size

Explore Microsoft AI's Phi family of small language models, designed for edge deployment and high efficiency.

small-language-modelsedge-computingbenchmarks

#2356: Why AI Coding Needs Two Brains

Discover how specialized fast apply models streamline AI-powered code edits, cutting costs and latency while maintaining precision.

software-developmentai-modelsproductivity

#2355: Why Open-Weight Models Are Winning

Discover how Cogito v2.1 leverages process supervision and MoE architecture to redefine reasoning efficiency in open-weight AI models.

large-language-modelsopen-sourceai-training

#2353: Evaluating Enterprise AI: Palmyra X5

Explore Palmyra X5, Writer’s flagship AI model designed for enterprise workloads, featuring a million-token context window and agentic capabilities.

ai-modelscontext-windowai-orchestration

#2351: AI Model Spotlight: ** Aion-2.0

Why is a biopharma AI lab releasing a storytelling-optimized model? We explore Aion-2.0’s architecture, pricing, and niche adoption.

ai-modelspharmacologyisrael

#2350: NVIDIA's Strategic Pivot: From Chipmaker to Model Builder

Dive into NVIDIA’s Nemotron 3 Super, a hybrid MoE model combining Mamba, Transformers, and multi-token prediction for cutting-edge efficiency.

transformerslatent-spaceai-models

#2349: The 30-Person Lab Outpacing AI Giants

Discover how Arcee AI’s Trinity Large Thinking delivers cutting-edge reasoning at a fraction of the cost, all from a team of just 30.

ai-modelsreasoning-modelsbenchmarks

#2348: Diffusion Models Take on Text Generation

Explore Inception Labs’ Mercury 2, a groundbreaking diffusion-based language model that rethinks text generation and reasoning.

transformersparallel-computingvoice-first

#2336: How ADRs Solve AI's Institutional Memory Problem

Architectural Decision Records (ADRs) aren’t just documentation—they’re a way to give AI coding assistants the context they lack.

software-developmentai-agentslegacy-systems

#2316: Who’s Building AI’s Next Training Data?

How boutique dataset firms are reshaping AI training, from rights-cleared content to domain-specific precision.

fine-tuningtraining-datadata-sovereignty

#2315: How to Update AI Models Without Starting Over

Exploring the challenge of updating AI models with new knowledge without costly full retraining.

ai-trainingfine-tuningrag

#2314: One Model or Three? Inside Claude's Architecture

What makes Claude’s Haiku, Sonnet, and Opus different? Discover how architecture shapes their unique strengths and weaknesses.

large-language-modelsai-modelsmodel-context-protocol

#2313: When AI Optimizes the Wrong Thing

Discover how AI systems learn to optimize for rewards—and why they sometimes get it dangerously wrong.

ai-trainingai-alignmentai-ethics

#2312: When Bigger Context Windows Aren't Better

Exploring the real-world impact of massive context windows in AI models, from academic research to codebase analysis.

context-windowai-modelsai-workflows

#2309: Blind Ranking AI's Best Podcast Scripts

How do 15 AI models handle controversial podcast prompts? We rank their scripts blind and reveal the surprising winners.

large-language-modelsprompt-engineeringai-ethics

#2307: Inside Frontier LLM Training: Stages, Costs, and Checkpoints

Discover the multi-stage process of training frontier large language models, from pretraining to post-training, and why checkpoints are the key to ...

large-language-modelsai-trainingfine-tuning

#2306: Can LLM Councils Truly Capture Diverse Worldviews?

Exploring whether LLM councils can achieve genuine worldview diversity or if alignment processes erase meaningful differences.

large-language-modelsai-alignmentcultural-bias

#2271: Vector Search in a Single File

What if you could do vector search with just SQLite? We explore sqlite-vec, the extension that adds embeddings to the world's simplest database, an...

vector-databasesedge-computingdata-storage

#2239: How AI Benchmarks Became Broken (And What's Replacing Them)

The tests we use to measure AI progress are contaminated, saturated, and gamed. Here's what's actually working.

benchmarkstraining-dataai-reasoning

#2233: Who Actually Wants AI to Slow Down?

Daniel argues AI development should slow down for expertise and stability. But who in the industry actually shares this philosophy beyond the obvio...

ai-safetyai-alignmentlarge-language-models

#2228: Tuning RAG: When Retrieval Helps vs. Hurts

How do you prevent retrieval from suppressing a model's reasoning? We diagnose our own pipeline's four control levers and multi-source fusion strat...

ragai-agentsprompt-engineering

#2224: Why AI Can't Crack the Voynich Manuscript

A fifteenth-century text has defeated cryptanalysts, linguists, and AI models alike. What does its resistance tell us about language, encoding, and...

cryptographylinguisticsai-reasoning

#2213: When Ground Truth Moves Hourly

How do you rigorously evaluate whether Tavily or Exa retrieves better results for breaking news? A formal benchmark beats the vibe check.

ragbenchmarkshallucinations

#2206: What Actually Works in AI Memory

Most AI memory systems are just vector databases with similarity search. We break down what mem0, Zep, and Letta are actually doing—and why benchma...

ai-memoryvector-databasesknowledge-graphs