Fine Tuning
178 episodes · Page 5 of 8
#4589: The Answer Reflex: Why AI Models Can't Follow Instructions
DeepSeek passes a simple test that stumps GPT and Claude. Why can't Western models stay in character?
#4492: What Makes a Container Robot-Ready?
The hidden specs that turn a plastic box into something a robot can pick, read, and move at industrial speed.
#4057: How to Fix AI's Bullet Point Addiction
Why AI models default to bullet points and how textual LoRAs achieve 94% prose adherence.
#3596: Why an AI Model Kept Calling Itself Sonnet 4.6
When a Chinese model insists it's "Sonnet 4.6," is it theft, sloppy training, or something stranger?
#3465: 10 Folders That Actually Earn Their Keep
Ten folders to organize your household and small business — plus the stationery that actually lasts.
#3406: LoRA Isn’t Just for Image Generation
LoRA lets you fine-tune an LLM’s behavior with a 50MB file. Here’s how it works and why it matters.
#3283: Fine-Tuning DeepSeek for One Podcast
Can a purpose-specific fine-tune fix a model's stubborn writing tics? We explore the practical engineering behind it.
#3212: Why Eilat Has 3 Airports for 55,000 People
Israel’s southernmost city is a tourism powerhouse with a neglected core. The VAT zone, land policies, and three airports tell the story.
#3157: Opus 4.8: What Actually Changed Under the Hood
Anthropic dropped Opus 4.8 with no fanfare. New training data, faster inference, and smarter refusals — here's what changed.
#2997: The Science of Great Hot Sauce
Why does one hot sauce taste complex while another is just gritty heat? It comes down to fermentation, particle size, and chemistry.
#2922: The Milk That Never Touched a Cow
Precision-fermented dairy is on shelves. But is it milk? And is it kosher? Three rabbinic positions, one yeast strain.
#2891: Do ADHD Drug Holidays Actually Work?
The science behind taking breaks from stimulant medication—does it reset dopamine or just disrupt treatment?
#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.
#2641: Bridging Analog and Digital Note-Taking
How Nano Banana finally solves the text rendering problem, turning messy whiteboard photos into polished tech diagrams.
#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.
#2636: Take Notes Like a Diplomat
What WikiLeaks cables teach us about capturing meetings: judgment over transcription, context over completeness.
#2544: How to Make AI Architectural Renders Photoreal Without Breaking Geometry
Fixing the uncanny valley in AI-enhanced architectural renders — without breaking the geometry.
#2517: How Unsloth Makes LLM Fine-Tuning 2x Faster
Unsloth cuts memory usage by 50-70% and speeds up training 2.2x for models like Llama 3 and Mistral.
#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.
#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.
#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.