Local AI
313 episodes · Page 7 of 14
#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.
#2693: When AI Ignores Your Style Guide
Why your AI ignores formatting instructions and how to fix it with pipeline architecture, not model swaps.
#2668: When a Flamethrower Is Overkill
Tesseract, EasyOCR, or a cloud vision model? How to build a fast, reliable label scanner for real-world conditions.
#2597: Voice Control for Renters: $25 Per Room, No Wall Damage
Distributed voice control on a budget with wake words, centralized processing, and zero wall damage — perfect for rentals.
#2591: Decoupling Script from Voice
How dynamic voice replacement could let listeners choose who narrates each host's lines.
#2567: Beyond Pixels: Controlling Apps Without Vision
How MCP agents can use accessibility APIs and COM to control Windows and macOS apps at the protocol level.
#2545: Visual AI Pipelines: Beyond Python Glue Code
From ComfyUI to Dify — a tour of visual tools for building modular AI workflows without writing glue code.
#2536: Self-Hosted Zapier Alternatives in 2026
n8n, Huginn, and Dagu compared for personal automation on your own hardware.
#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.
#2512: How Speech-to-Speech Models Eliminate the Robot Voice
Why AI voice agents sound robotic, and how natively integrated speech-to-speech models fix 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.
#2488: Hybrid Pipelines for Entity Resolution
Classic NLP pipelines vs. lightweight LLMs for handling Hezbollah’s half-dozen spellings.
#2486: Why Noise Reduction Can Ruin Transcription Accuracy
Cleaning audio before transcription can increase errors by up to 46%. Here's the right approach for your voice app.
#2483: Substitution Anonymization: Privacy Without Utility Loss
How to generate realistic synthetic voice notes and calendar data with zero PII exposure risk.
#2470: Where Intelligence Should Live in Your Pipeline
When should you fine-tune a tiny model for prompt enhancement instead of prompting a large one? The answer depends on latency, precision, and domain.
#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.
#2431: The 3 Markets in an AI Trench Coat
GPUs, LPUs, and ASICs: why the best hardware for AI depends entirely on what you're trying to do.
#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.
#2398: Your Taste, Your Data: Owning Your AI Preferences
Why can’t you describe your perfect movie—but you’d know it if you saw it? A vision for portable, user-owned AI taste profiles.
#2358: ESP32 vs Raspberry Pi: The Microcontroller Mindshift
Why your smart thermostat doesn’t run Linux—and why that’s a feature. The surprising differences between microcontrollers and single-board computers.
#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.
#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.
#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.
#2352: The Structured Output Gap in Vision APIs
How do object detection APIs like Gemini, AWS Rekognition, and YOLO compare for automated annotation workflows?