Fine Tuning
178 episodes · Page 4 of 8
#5533: Why AI Characters Drift Between Shots
Why does your AI character look like a different person by shot four? The answer is structural — and the fix isn't what you'd expect.
#5520: Keeping a Fine-Tune Alive Across Model Releases
Daniel wants to fine-tune DeepSeek Flash 4.1 on edited podcast scripts. The hard part isn't training — it's surviving the next release.
#5485: Fine-Tuning Parakeet for Hebrew and Your Own Jargon
NVIDIA's Parakeet beats Whisper on Android — but can you teach it Hebrew, or just your own jargon? Two answers, one much happier.
#5443: Heads vs Layers: How Model Merging Actually Works
Heads aren't the Lego bricks of model merging — layers are. Here's what heads really do and how frankenmerges get built.
#5431: The Other Half of Hugging Face: Why BERT Still Out-Downloads Llama
Encoder models pull over a billion downloads a month. Decoder models pull 397 million. The AI conversation and the download counter are describing ...
#5412: Editing vs. Note-Taking for AI Fine-Tunes
Hand-editing a model's output gives three training signals at once. Writing notes gives one — and a weaker one at that.
#5411: Fine-Tuning at 4-Bit vs 16-Bit: What It Really Costs
QLoRA cuts fine-tuning VRAM 15x and cost up to 85% — but you pay in training time, quality, and safety alignment.
#5410: Adapters: 102KB That Reshapes a 403GB Model
A 102KB adapter file changes how a 403GB base model behaves — without ever merging into it. Here's how model adapters actually work.
#5409: What Makes a Model "Agentic"? Atria Dawn Preview
A 744B-parameter model drops quietly on Hugging Face. Is "agentic" a real model category, or just a deployment pattern?
#5408: When Small NLP Models Beat the LLM
Feature extraction, fill-mask, token classification — the classic NLP tasks still have a job. Here's when a small model beats a frontier API.
#5407: Hemmingway-1 and the War on Waffle
A 27B model promises answers without the preamble. Its benchmark is homegrown — and the behavior it targets has a paper trail.
#5393: Fine-Tuning a Model on 100 Hand-Edited Answers
You don't need 10,000 examples to make a model sound like you. The real number is closer to 100 — if the edits are opinionated.
#5341: The Bankruptcy Stone and the Debtor Blacklist
From Florence's stone of scandal to China's debtor blacklist, a tour of the world's most degrading insolvency rituals — and why the U.S. version is...
#5245: Training a Model on 100 Phone Photos
One drawer of screws, a hundred phone photos, and a schema. When does a small custom model beat a fine-tuned VLM?
#5169: Fine-Tuning vs From-Scratch for Minor Languages
What 774 experiments and a new Armenian model reveal about the tradeoff between fluency and knowledge in low-resource languages.
#5118: Model Identity Fraud: Distillation or Data Contamination?
When AI models lie about who they are, is it stolen knowledge or just contaminated training data?
#5116: Beyond Common Crawl: The Datasets Shaping AI
Common Crawl is just the bulk flour. We explore the curated datasets that actually shape what AI models know and do.
#5012: Masked Safety: How Post-Training Changes AI Behavior
Safety mechanisms aren't erased in post-trained models—they're masked. Here's how that changes everything for military AI.
#5011: Claude Gov: The Military's Forked AI
What the Pentagon actually got from Anthropic — and why post-training changes everything about AI alignment.
#4971: Fine-Tune vs Prompt: Taming Hallucinated Deadlines
Big models add fake deadlines. Small models miss tasks. Which wrongness can you build a system around?
#4969: How to Train a One-Class Detector from 300 Photos
From photo folder to production YOLO model — the real walkthrough for custom object detection.
#4809: Can a Podcast Train Itself?
Can a podcast become a self-developing project? We explore RAG vs. fine-tuning for lore memory.
#4723: Are Model Families Actually Different Models?
Claude Opus, Sonnet, and Haiku aren't trim levels — they're different models sharing a brand name.
#4669: What "Distribution" Really Means in AI Models
Unpacking what "distribution" actually means under the hood — and why training data variety shapes model behavior.