Artificial Developer Intelligence
Three engineer friends argue about AI so you don't have to. Model releases, research papers, tools, and the occasional existential crisis — no LinkedIn cringe required.
Latest Episodes
Ep 25 May 12, 2026Elon vs OpenAI Trial Drama, Billion Token Context Race, Multi-Agent Patterns 2026
Why is Anthropic now running on Elon Musk's GPUs — right after Elon sued OpenAI for the same kind of behavior? Why does breaking the context-window bandwidth wall require entirely new GPU architecture? And what does it mean when even Simon Willison admits he runs Claude Code with --dangerously-skip-permissions by default? Shimin, Dan, and Rahul cover Brockman's leaked deposition journal and the Tesla painting saga, the Anthropic-SpaceX/XAI Colossus One compute deal, NVIDIA's Rubin CPX disaggregation architecture on the road to a billion-token context, Phil Schmid's four sub-agent patterns for 2026, Jack Clark's 60%-by-2028 prediction for automated AI research, Simon Willison's reluctant embrace of vibe coding, Dexter Horthy publicly recanting on dark-factory agents, James Shore on why productivity gains evaporate without inverse maintenance gains, and Grok's collapse from 20M to 8M downloads.
Ep 24 May 8, 2026OpenAI's Goblin Problem, 10 Lessons When Code Is Cheap, AI Addiction Loop
Why does OpenAI's leaked Codex prompt forbid goblins, gremlins, and pigeons? Why is OpenAI gating GPT-5.5 Cyber after dissing Anthropic for gating Mythos? And what does it mean that Dan tried to write code without Claude and physically couldn't? Shimin, Dan, and Rahul cover the Codex CLI system prompt leak and RLHF post-mortem, Addy Osmani's long-running-agent patterns, Jesse Vincent's adversarial-review prompt, Drew Brunig's 10 lessons for agentic coding, Ivan Turkovic's history of programmer-elimination tools, Nilay Patel's software-brain thesis, a Nature paper on warm-model sycophancy, and Dan's three-month AI addiction loop.
Ep 23 Apr 28, 2026Why Models Over-Edit Your Code, Meta Keystroke Surveillance, Interviewing Engineers in the AI Age
Is GPT-5.5 finally a 4.7-tier model? Did DeepSeek V4 just close the gap with Anthropic? And what does it mean that a senior ML engineer says he can't out-code Claude anymore? Shimin, Dan, and Rahul are joined by special guest Nathan Lubchenco (The Future Was Yesterday) to cover OpenAI's GPT-5.5, DeepSeek V4 (1.6T base / 49B active / 1M context), Meta's Model Capability Initiative tracking US-employee keystrokes and mouse movements, a Levenshtein-distance study on coding-model over-editing, the 2026 Stanford AI Index, and a deep-dive on how to hire software engineers when the agents are already better at coding than the candidates.
Ep 22 Apr 21, 2026Is Claude Opus 4.7 Mythos Distilled, Running Qwen 3.6 Locally, and the AI-On-AI Arena
This week Shimin, Dan, and Rahul ask whether Claude Opus 4.7 is a distilled mythos slice and whether open source is dead after mythos, set up Alibaba's Qwen 3.6 35B A3B locally as Shimin's new Pi Agent driver, watch Simon Willison's Pelican-on-a-bicycle benchmark break for the first time, run an AI-on-AI Arena grading 11 frontier models, and cover cal.com going closed source, Jesse Vincent's rules-and-gates technique, a HIPAA-violating vibe-coded patient portal, Kyle Kingsbury's 'future of everything is lies', and Paul Graham's railroad-vs-AI-capex bubble comparison.
Ep 21 Apr 17, 2026Anthropic Mythos & Project Glasswing, Recursive Improving Agents, and Your Parallel Agent Limit
This week Shimin and Dan (Rahul is out on vacation) unpack MiniMax M2.7 and the first experimental evidence of recursive self-improvement, Anthropic's Mythos model and Project Glasswing — a cybersecurity-capable model being withheld while major corporations and the Federal Reserve patch infrastructure first — Adam Argyle on why AI sucks at front-end, Addy Osmani's framework for finding your parallel agent limit, Pierre Villega on code commoditization and industrialization, Dan's rant about installing Claude Code on WSL, and two minutes to midnight with new financial signals from the AI bubble.