Local AI
313 episodes · Page 5 of 14
#5390: Chaining Small Models for Dictation Cleanup
Daniel's Android dictation fork won't render "three point five" as a decimal. How many models does cleanup actually need?
#5389: Hugging Face vs Kaggle: Where Models Actually Live
Hugging Face and Kaggle aren't rivals — one is infrastructure, one is a practice field. Here's how the two platforms actually differ.
#5388: Android's Split Keyboard and Voice Input Problem
Android separates keyboards from speech engines by design. Most apps weld them back together.
#5387: Who Decides What Your Keyboard Knows?
Your keyboard's word list was probably frozen in 2014. Here's who maintains the open-source dictionaries — and why Gboard's stays fresh.
#5384: Android ASR Runtimes: LiteRT, ExecuTorch, and Why Your Phone Has No VRAM
Why does your phone have no VRAM number? A tour of Android's runtime layer and what it takes to run ASR locally.
#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?
#5188: DeepSeek's Point Release That Isn't
DeepSeek shipped a whole new architecture and called it a point release. Here's what actually changed inside the model.
#5154: DeepSeek's Two-Endpoint Philosophy
DeepSeek quietly routed Pro traffic to Flash — and that routing change says everything about its two-endpoint strategy.
#5054: Hardware Clubs for Grownups: Finding Your People
Software is solitary. Hardware is social. Here's how to find or build a space where adults and teens build together.
#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.
#5004: What Precision Is Your Model Actually Running At?
When you call an API, are you getting the model you think you are? Inference providers quantize more than they admit.
#5000: Can You Trust Google Photos With Your Life's Work?
Why your Google Photos library isn't really backed up — and what actually works instead.
#4981: The Void That Doesn't Heal
Why the grief of not having supportive parents feels different — and what neuroscience reveals about it.
#4973: Building a Pure AI Inference Server
Why your "AI server" should look more like a database than a web app, and how to actually build one.
#4972: CPU vs GPU Inference: When to Skip the GPU
Why running AI on CPU isn't a toy — and when the GPU advantage vanishes.
#4970: Labels vs. Book Covers: Structured Extraction Tradeoffs
General vision models vs. purpose-built pipelines for extracting data from messy real-world labels and covers.
#4967: AI Gateways: Worth the Middleware Tax?
When does an AI gateway's overhead justify its features? We break down the tradeoffs.
#4966: Local vs Cloud: Running Hugging Face Models
Hugging Face's compatibility tracker, cache management, and the real difference between Inference Endpoints and the direct API.
#4920: Local Dictation on Android: The Real Bottlenecks
Why on-device speech-to-text on Android hits a wall at 30 seconds — and what silicon actually matters.
#4919: Parakeet vs Whisper: On-Device Dictation Showdown
NVIDIA Parakeet beats Whisper on phone dictation despite having more parameters. Here's why architecture matters more than model size.
#4832: Your AI Memory Should Be Markdown Files
Why your AI project memory should live in Git-tracked Markdown files, not a proprietary platform.
#4822: Cloud-Local AI Hybrid: Does It Actually Work?
Can you pair Claude's reasoning with a local Qwen 7B for savings? The gap is wider than you think.
#4789: How LLMs Actually Know When to Stop
Three layers of stop signals, from EOS tokens to context limits — and why none of them really "know" when to stop.
#4778: SSH MCP and Tailscale: Docker Migration Guide
How to configure Tailscale for Docker containers when migrating from public IPs to tailnet addresses.