Open Source
596 episodes · Page 4 of 25
#6134: Cheap Tokens, Expensive Scripts
A model with worse list prices can cost less per script — if the cache hits. The bill hides in tokens, not rates.
#6130: Picking a Human Labeling Tool for LLM Benchmarks
Building a human review layer for LLM benchmarks? Here's what Argilla, Label Studio, Prodigy, and Potato actually cost in money and maintenance.
#6129: How to Build an AI Preference Dataset
Pairwise comparison, forced choice, or just "this one or that one" — the engineering behind collecting human preferences on AI outputs.
#6126: Can You Train a Machine to Be Funny?
Comedy fights everything next-token prediction is built for. Turns out you can train a model to land a joke — and then measure it.
#6123: OAuth or a Personal Access Token for Your MCP Server?
GitHub CLI login hands your agent one long-lived token with access to everything. Fine-grained PATs can't. Which should your MCP server use?
#6115: Claude Cracked the NSA's 1997 Curve Seeds
A 25-year crypto mystery solved in under 30 minutes — by finding a bit that wasn't there.
#6111: Translation Models That Know Drama From Contracts
Specialist translation models beat general ones on benchmarks — then lose the human vote. What actually ships when you need a register, not just a ...
#6104: Mistral AI : le pari européen de la souveraineté en intelligence artificielle
Comment Mistral AI défie la Silicon Valley avec des modèles efficaces, des partenariats stratégiques et son nouveau modèle vocal Voxtral ? Corn et Herman font le point.
#6099: Code-First Workflow Runners: Prefect, Temporal, Dagster
Your workflow lives in git, your GUI is just a window, and your worker actually runs the jobs. Which runner wins?
#6092: 到底是谁在塑造中国的人工智能思想？
不只是实验室的老板：那些定义中国如何打造、又如何争论人工智能的研究者和思想。
#6087: Building a Podcast Graph That Doesn't Suck
Daniel wants to turn a 6,000-episode archive into a walkable graph. Turns out the hard part isn't the database — it's the pruning.
#6086: Reading Polymarket as an OSINT Feed
Polymarket's API turns prediction market prices into a live probability feed — no wallet, no trading, just reading the world's largest market.
#6069: The Whole Machine: How an Episode Gets Made, Send to Publish
The complete tour of the pipeline that makes the show, stage by stage, from the send form to publishing, including the new eight-turn batched voice decode.
#6062: Who Actually Shapes Chinese AI Thinking?
Beyond the lab CEOs: the researchers and ideas defining how China builds — and argues about — artificial intelligence.
Also available in:中文
#6054: Seven Percent for a Decade: What Open Data Portals Actually Delivered
A decade of open data portals moved the share of fully open datasets from 7% to... 7%. What would a real publishing pipeline look like?
#6052: What's Actually in the Hugging Face ASR Catalog?
Four real architectural bets sit underneath thousands of Hugging Face ASR repos. Here's how to tell the bets from the repackagings.
#6051: How to Find the AI Benchmark You Actually Need
Thousands of benchmarks, no canonical index. How Benchmark Radar and the Lighteval Tasks Explorer help — and where they fall short.
#6048: Under the Hood, October 2026: Seventeen Prompt Versions and Three-Times-Faster Voices
Four weeks of pipeline changes, grounded in the code: grace periods, duplicate detection, Hilbert's rules, echo deletion, and voices nearly three times faster.
#6047: A Human Guest on His Own AI Podcast
Daniel built an AI podcast with cloned voices — then sat down as a guest on it. What six thousand episodes taught him about prompts.
#6039: Who's Actually Building Frontier AI Outside the US and China?
Mistral sits 20 points off the frontier. Korea runs a bake-off. The UAE open-sources everything. What's actually driving sovereign AI?
#6038: The Model You Pay For Isn't the Best Deal
Eight Chinese labs, two tiers each, and a pricing spreadsheet that says your default model is mid-pack.
#6035: Who Else Is Making AI Podcasts? A Survey
A survey of AI-hosted podcasts: one full match, a 730-episode run, a home NAS rig, and a graveyard of good tooling.
#6005: What's Actually Behind a Government AI Chatbot
Singapore runs open-weight models on commercial cloud. The UK built its own chatbot, then shut it down for Copilot. What's really behind civil-serv...
#6001: What Do Inference Providers Actually Sell?
Same open weights, 20x cost gap. What Fireworks, Together, and Groq actually sell — and when to just rent a GPU.