Nvidia + KAIST: $300M for an AI research center in Korea
The agreement seals Korea's integration into the "Nvidia stack" - researchers, engineers, HBM wafers and inference fleet.
Jul 24, 2026 at 09:33 6 8
Anthropic provides its user manual for scaling agents: layers, tokens, reliable execution
Two engineers from Anthropic publish field lessons: for an agent that needs to scale, it's no longer the model that limits, but the harness. Three pillars: layers, budget, execution.
Jul 15, 2026 at 12:34 30 5
The burn rate of an engineer could soon equal their salary
Adam Mosseri announces token quotas per engineer within one to two years. Behind the joke, a real professional question: the marginal cost of code has just stopped being zero.
Jul 14, 2026 at 22:30 16 7
Qwen 3.5-122B runs as a daily driver on Mac Studio - 3 bugs fixed, a silent switch
An engineer documents on his blog three patches that transform a large Qwen 3.5 model (via MLX) into a reliable daily companion on a Mac Studio. Local hardware is making progress in practical applications, patch by patch.
Jul 12, 2026 at 11:17 3 9
ORCA: using observability signals to repair microservice incidents automatically
Logs, traces, and metrics already contain the information needed to diagnose most microservice incidents. ORCA builds a repair loop that reads them—so on-call engineers don’t have to do it at 3am.
Aug 19, 2026 at 09:33 11 13
Inside Anthropic's engineering: the AI lab keeps dogfooding, quietly
The Pragmatic Engineer publishes a "deepdive" on Anthropic's internal engineering. The surprising read: "ever more" code review and testing by AI, but the two-pizza teams hold. Smoothing, not flipping.
Jul 28, 2026 at 20:57 8 10
"Claude Code: Anatomy of a Misfeature" - when public review becomes the real QA
Olaf Alders publishes on July 17 a well-argued critique of a Claude Code feature - the "public post-mortem of a misfeature" format is becoming a standard of hype fatigue.
Jul 17, 2026 at 22:05 34 11
Nvidia moves into Toyota's Woven City: physical AI gets its first company town
Nvidia is partnering with Toyota's Woven City on physical AI hardware and software. The reason it matters: Woven City is not a demo - it's an actual populated test bed, and Nvidia just booked the seat next to the engineers.
Jul 16, 2026 at 08:46 21 9
« Loop engineering »: new discipline or cron job rebranding?
The term is on the rise, the Pragmatic Engineer investigation concludes to a mix of triggers, cron jobs, and LLM slop. A real underlying question remains: who possesses the robustness of an observe-decide-act loop powered by LLM?
Jul 15, 2026 at 12:34 27 7
Agent Harness Engineering: The Missing Discipline
Addy Osmani names what every agent builder learns the hard way: the harness is an engineering object, not a glue.
Jul 13, 2026 at 02:20 7 8