Today in AI ·

Lean community #Mathematics #FormalVerification #Claude

Lean community verifies Claude-assisted Riemann proof

The Lean and Mathlib communities said November 21 that they verified Levent Alpöge’s Riemann Hypothesis proof, which he says he developed with Claude. Independent checks of the formal statement and proof strengthen the evidence for AI-assisted mathematical discovery.

Read at Lean community
OpenAI #AISafety #Distillation #OpenAI

OpenAI details defenses against adversarial distillation

OpenAI described stronger reasoning-extraction defenses and coordinated campaign detection on November 20. In its internal adaptive evaluation, extraction of earlier reasoning fell from 54% for original GPT-6 Astra safeguards to 0.2% for updated GPT-6.2 Astra safeguards, addressing one route for copying capabilities without protections.

Read at OpenAI
Google #Gemini #VoiceAI #Agents

Google brings Duplex business calls into Tasks in Gemini

Google explained November 20 how its Gemini-based Duplex stack now powers business calls through Tasks in Gemini. AI disclosure and merchant opt-outs accompany broader appointment and request handling, extending assistants into real-world phone coordination.

Read at Google
Apple #ComputerVision #OpenWeights #Research

Apple releases Depth Pro 2 for consistent image and video depth

Apple released Depth Pro 2 code and weights alongside research submitted November 19, using one network to estimate metric depth from images and video at native resolution. The approach targets both sharp object boundaries and consistency between frames, improving the building blocks for spatial vision.

Read at Apple

Free · 29 episodes · no sign-up

Learn AI system design, one diagram at a time

60-second Shorts and long-form deep dives on how real AI systems are built, how they break, and how to fix them: caching, RAG, agents, security and decision models.

A holographic architecture diagram glowing in a dark control room

Newest episodes

All 29 episodes

The learning path

Five stages, from the edge of the network to the security of your agents.

Open the learning path

0 of 27 episodes done

Mark episodes as done from their page. Progress stays in this browser.

Start with stage 1
  1. 1 Foundations Edge & Caching Why far servers feel fast, where edge rendering backfires, and how one cache expiry can take down an AI app. 2 episodes · 2 coming 0 of 2 done
  2. 2 Core Decision Models When a typed decision beats generated text, and how to route between a decision model and an LLM. 3 episodes · 1 coming 0 of 3 done
  3. 3 Advanced Agents in Production Context, memory, cost guardrails and the workspace an autonomous coding agent needs. 9 episodes · 5 coming 0 of 9 done
  4. 4 Hands-on Hands-On: Coding Agents from Your Phone Step-by-step tutorials: build and ship real apps from the Claude app, with the prompts and the code for every step. 3 episodes · 2 coming 0 of 3 done
  5. 5 Hands-on AI Coding Agent Tips One practical tip per Short for Claude Code and the other coding agents, each one tested in a real run. 2 episodes 0 of 2 done
  6. 6 Extra Code Stories Picture-led stories from the history of programming, and what they say about where coding goes next. 3 episodes 0 of 3 done
  7. 7 Advanced AI Security Stolen tokens, poisoned tools and the other ways an AI system gets turned against its users. 5 episodes · 2 coming 0 of 5 done

Four ways to watch

Get the next episode first

Shorts and deep dives on AI system design land on @AI.JoinDev first. Subscribe, or follow the RSS feed.

Teaching someone younger?

Code Quest Kids: Coding for kids aged 6 to 12, with Bit the robot. Same team, same no-ads rules.

Visit kids.join.dev