Blog 388 posts

Notes from the trenches on AI engineering, LLM apps, and the full-stack work that holds it all together.

Why solo AI agents break when you add a second user
6 min read

Why solo AI agents break when you…

Solo coding agents like Claude Code and Cursor are brilliant for one power user. At team scale, context compaction, siloed memory, and local credentials turn small wins into operational risk.

Starcloud raised $250M to put Nvidia GPUs in orbit
5 min read

Starcloud raised $250M to put Nvidia GPUs…

Starcloud's Series A extension values the orbital data center startup at $2.3B. Nvidia and Cisco joined Manhattan West on a round meant to fund manufacturing, launches, and the Vera Rubin Space-1 chip partnership.

VGGT-Omega scales 3D reconstruction to 10B parameters with 70% less training memory
7 min read

VGGT-Omega scales 3D reconstruction to 10B parameters…

Meta and Oxford's VGGT-Omega is a CVPR 2026 oral that cuts GPU training memory by roughly 70%, scales to 10B parameters, and beats optimization pipelines on dynamic scenes. Here's what changed and how I'd evaluate it before betting a product on feed-forward 3D.

The FDA just cleared a robot that draws blood without a human holding the needle
4 min read

The FDA just cleared a robot that…

Vitestro's Aletta received FDA De Novo authorization for autonomous phlebotomy: vein imaging, needle insertion, tube swaps, and bandaging. I unpacked the trial numbers and what a 1-to-3 staffing model means for clinics.

Waymo built a custom 5nm chip because robotaxi compute is not a data center problem
4 min read

Waymo built a custom 5nm chip because…

Waymo revealed a purpose-built 5nm ASIC for front-end sensor processing, 1,000+ TOPS onboard, and 20x compute scaling in eight years. I mapped what that means for anyone shipping physical AI at the edge.

ByteDance Lance: a 3B model that reads, generates, and edits images and video in one stack
6 min read

ByteDance Lance: a 3B model that reads,…

Lance is ByteDance's Apache 2.0 unified multimodal model at 3B active parameters. It handles captioning, VQA, text-to-video, and multi-turn edits in one framework, trained on 128 A100s. Here's what that means if you ship generative media.

DoorDash pays Dashers $5 to load Dot robots. The last 10 feet still need humans.
5 min read

DoorDash pays Dashers $5 to load Dot…

Dot can drive 20 mph on roads and sidewalks, but it cannot pick up a bag at the counter. DoorDash's Phoenix pilot pays gig workers to bridge that gap. That handoff problem shows up in every ops automation project.