Podcast Episodes
Back to Search
Can You Version-Control Your Android Apps?
Episode 5417
Android Developer Verification enforcement began this month in Brazil, Singapore, Indonesia, and Thailand, and F-Droid says it can't comply. Meanwhil…
3 weeks, 4 days ago
Xet, Buckets, and Auto-Pulling Model Weights
Episode 5416
Hugging Face quietly migrated 500,000 repositories and 20 petabytes to Xet, a chunk-level dedup engine that replaced file-level Git LFS. This episode…
3 weeks, 4 days ago
Inside F-Droid: Repos, Front Ends, and Sideloading Safely
Episode 5415
F-Droid has been the oldest surviving alternative to the Play Store since 2010 — and its small catalog is a feature, not a bug. This episode unpacks …
3 weeks, 4 days ago
Inventing Anna: The Real Tradecraft Behind the Con
Episode 5414
Anna Delvey defrauded banks, hotels, and New York's elite without hacking a single thing. Her entire toolkit was Microsoft Word, fake AOL accounts, a…
3 weeks, 4 days ago
Who Actually Picks Your In-Flight Movie?
Episode 5413
Eight in ten passengers use the seatback screen, and the Big Four US carriers alone carry over 525,000 of them. Yet the teams choosing what plays on …
3 weeks, 4 days ago
Editing vs. Note-Taking for AI Fine-Tunes
Episode 5412
Daniel wants a daily AI assistant that writes like him, and he's weighing two ways to get the training data: hand-editing the model's responses, or l…
3 weeks, 4 days ago
Fine-Tuning at 4-Bit vs 16-Bit: What It Really Costs
Episode 5411
What actually happens when you fine-tune a quantized model instead of the original weights? This episode walks through the mechanics of QLoRA versus …
3 weeks, 4 days ago
Adapters: 102KB That Reshapes a 403GB Model
Episode 5410
A 403GB base model, a 102KB adapter file, and a deliberate choice never to merge them. This episode unpacks what a model adapter actually is — formal…
3 weeks, 4 days ago
What Makes a Model "Agentic"? Atria Dawn Preview
Episode 5409
A 744-billion-parameter model appeared on Hugging Face with no announcement, no paper, no API, and no independent evaluation — but a grand title ("Th…
3 weeks, 4 days ago
When Small NLP Models Beat the LLM
Episode 5408
Every language problem gets routed to a frontier text-generation model these days — and sometimes that's exactly the wrong engineering choice. This e…
3 weeks, 4 days ago