Training Data
322 episodes · Page 8 of 14
#2774: Open Data That Actually Works
The gap between open data promises and reality, and the rare cases where it actually changes policy.
#2761: When a Strong Shekel Rewrites Labor Economics
How a surging shekel is reshaping Israel's labor market, crushing exporters, and creating unexpected winners among foreign workers.
#2754: Why Your Dictation Setup Might Be Wrong
Modern ASR is shockingly robust. The biggest predictor of accuracy? How well your audio matches its training data.
#2664: Can You Trust an LLM's Raw Knowledge?
Why pre-trained knowledge isn't reliable for facts — and what actually makes models useful.
#2651: AI Training Itself: Student, Teacher, and Grader
Can models generate their own training data and judge their own outputs? The promise and pitfalls of fully AI-led pipelines.
#2640: Why Instructional Models Beat Conversational for Batch AI
Beyond cheaper tokens—how batch inference changes AI workflows and why instructional models beat conversational ones for automated jobs.
#2622: How Transformers Actually Work: Attention, Tokens, and Context
How one architectural change unlocked chatbots, image generation, and protein folding — explained without the jargon.
#2546: The Invisible Engineering Behind a Single Click
The technical stack behind click-to-edit features in tools like Canva and Google Photos — from segmentation to inpainting.
#2539: When Does AI Stop Hallucinating and Start Reconstructing?
What happens when you feed hundreds of photos into an AI world generator — do you capture reality or just a convincing dream?
#2516: Overfitting Is Not a Binary Condition
Overfitting isn't binary. Learn the real triggers, the bias-variance tradeoff, and modern techniques to prevent it.
#2495: How to Bake Personality Into an LLM in 15 Minutes
Fine-tune a model's personality with ~300 examples and a consumer GPU. SFT + DPO explained.
#2494: Active Prompt Engineering: Daniel's Diff-Based Loop
A deep dive into iterative prompt refinement using inter-iteration prediction change as an uncertainty signal.
#2489: When Trust Moves Markets: The Euro-Shekel Story
How the euro-shekel exchange rate impacts Israeli exports, imports, and the broader EU trade relationship.
#2488: Hybrid Pipelines for Entity Resolution
Classic NLP pipelines vs. lightweight LLMs for handling Hezbollah’s half-dozen spellings.
#2487: Why AI Calls Everything a "Prediction" (Even Images)
Machine learning calls everything a "prediction" — even generated images. Here's why the terminology matters more than you think.
#2483: Substitution Anonymization: Privacy Without Utility Loss
How to generate realistic synthetic voice notes and calendar data with zero PII exposure risk.
#2467: The Time Tax on API Access
How OpenAI and Anthropic structure API tiers, rate limits, and why your billing history matters more than you think.
#2466: The Hidden Trap of Embedding Model Lock-In
What happens when your vector database works great — until your embedding model gets deprecated and your vectors become useless.
#2464: Batch APIs: The 50% Discount You're Probably Misusing
Batch inference APIs offer 50% off — but only for the right workloads. Here's when they actually make sense.
#2452: When BIM Breaks the SQL Analogy
How BIM's cascading changes eliminate coordination errors — and where the SQL analogy breaks down.
#2426: Why DeepSeek V4's Prose Feels More Vivid Than Claude or GPT
A million-token context window at 2% the KV-cache cost — and prose that actually breathes. Here's what makes V4 different.
#2411: Are Political Bias Benchmarks Actually Measuring Anything?
Why the Political Compass Test fails, and what researchers are building instead to actually measure model bias.
#2409: When AI Cheats on Cultural Knowledge
Five benchmarks that reveal how AI systems fail at cultural knowledge — and what their methodologies tell us.
#2408: How Backpropagation Actually Unlocks Neural Networks
How error signals flow backward through networks to make learning possible — and why "it's just calculus" misses the point.