#ai

Local AI Video Models on a DGX Spark: the Scene Renders, the Verb Does Not

“Grade on geometry and object identity, never on vibe. Materials lie convincingly.”

FLUX Can Spell, SDXL Cannot: Local AI Image Models on a DGX Spark

“A caption written after looking will always find something to praise.”

Forty-Four Harness Bugs, Zero Local LLM Limitations: an Accounting

“A model that looks broken is a harness bug until proven otherwise.”

Nine Local LLMs Ranked by Cost Per Solved Task — Seven of Them Have No Price at All

“A repair that doesn't satisfy the contract isn't 80% of a repair. It's a workspace you throw away.”

What a Bug Fix Costs on Two DGX Sparks: 16 Concurrent AI Agents, 4.45× Cheaper Than Serial

“The ceiling I'd been running against was a benchmark's sample size, not a limit of the machine.”

Nine Lines of Verification That Beat a Six-Agent AI Swarm

“It tried to stop 52 times. It was refused 51. That is the whole mechanism.”

1,200 Lines of Multi-Agent Orchestration, Beaten by One Local LLM Agent

“The orchestration didn't lose because multi-agent is a bad idea. It lost because it was insurance against a blindness that no longer existed.”

The Day I Lost to Tensor Parallelism: Nemotron-70B Across Two DGX Sparks

“The right response to 'the weights don't fit' was to shrink the weights, not to distribute them across a fabric with a documented collective bug.”

The Agent Framework Bake-Off: LangGraph vs Pydantic AI vs Hand-Rolled, and the 32 Lines That Mattered

“The gain didn't come from primitives. It came from 32 lines being harder to get wrong.”

Twenty-Two Behavioural Criteria: What Replaced the Structural Grader My AI Agents Kept Fooling

“Scoring went from 28 seconds to 2, and got strictly harder to fool.”

The AI Grader That Passed the Same Bug Three Times: 229 Checks, Three Agent Workspaces, One Blind Spot

“A perfect score, three times, over the same bug. The checks weren't wrong. They were pointed at the wrong thing.”

Ten AI Agent Frameworks on Paper: LangGraph, DSPy, CrewAI and Seven More, Scored Against a Local LLM

“Every framework surveyed leaves the orchestration logic as code you write either way.”

Sixteen Requirements for an Agentic Coding Swarm, All of Them Scar Tissue

“Last-writer-wins is invisible to any score-based gate. The work vanishes and the number goes up.”

A Scorecard, Not a Vibe: What I'd Need Before an AI Coding Agent Touches My Codebase

“An agent asked to judge its own completion will do what anything does in that position.”

The Local LLM Bill: What a Bug Fix Has to Cost Before Two DGX Sparks Make Sense

“Per-token pricing prices the tokens you burn, and search burns tokens by design.”

Agent-based DevOps with Q Developer — kept vs tossed

“An agent that's wrong 5% of the time is not a 5% problem. It's a trust problem with a percentage attached.”

IoT & Connected Devices — 2026 Predictions and Outcomes

“Smart glasses in 2025 are where smart speakers were in 2017 — the breakout product everyone's heard of but only one in four households owns. The chasm crossing happens in 2026.”

Strands + AgentCore — a year-end agent-stack inventory

“Pick the framework that matches your team's experience, not the one with the loudest blog posts.”

Bedrock AgentCore at Summit NY — what it actually changes

“AgentCore is what Bedrock Agents should have been from the start. That doesn't make it the wrong answer now.”

Knowledge Bases for Bedrock in production — the gotchas list

“Managed RAG is 80% of the work. The other 20% is most of the production headaches.”

IoT & Connected Devices — 2025 Predictions and Outcomes

“The flagship category creators of 2024 (Vision Pro, AI Pin, Rabbit R1) all sold under 500K units. The quiet success (Ray-Ban Meta) sold 2M+. Glasses won. Headsets and pins lost.”

Bedrock Agents, half a year in — the parts I actually use

“Agents are router code with model-shaped opinions. Useful, but not magic — and that's exactly why I kept some of it.”

Rock Product Decisions With Data

“Why Data is Your Product BFF Imagine you’re crafting a killer playlist. You wouldn’t just throw on any old tunes, right? You’d consider the vibe, the listener, and what’s to…”

IoT & Connected Devices — 2024 Predictions and Outcomes

“The AI hardware category in 2024 is going to learn the same lesson the AR glasses category learned in 2016: shipping a sci-fi product without a real use case kills the funding round and the company.”

10 Game-Changing Project Management Trends to Dominate 2024

“Hold onto your Gantt charts, PM warriors—2024 will rewrite the rules of project management. Based on emerging patterns and tech breakthroughs, here’s what’ll shake up your workflow: 1. …”

First week with Bedrock: a PM's read on the September GA

“Bedrock isn't a model — it's the absence of a vendor lock-in argument.”

Prompt regression — the rough first version of our test set

“We're testing prompts the same way we test code. We just haven't earned the vocabulary yet.”

Behavioral AI on pet cameras — what works, what's marketing

“The behavioral AI that works in 2023 lives in veterinary clinics with $40,000 high-frame-rate cameras and trained-classifier pipelines for lameness detection. The behavioral AI on a $250 consumer camera doing 'is your dog happy' is marketing. The category distinction matters.”

IoT & Connected Devices — 2023 Predictions and Outcomes

“The phone is mature. The watch is mature. The next interface is the one you put on your face — but 2023 is the announcement year, not the ship year.”

2023 Project Management predictions and demize!

“Let’s face it: 2023 will be the year project managers either ride the wave of change or get crushed by it. Buckle up as we unpack the seismic shifts transforming workflows, tools, and team…”

10 Game-Changing Project Management Trends for 2019

“1. AI: Your New BFF (Best Forecasting Friend) Forget crystal balls – Artificial Intelligence is the fortune-teller of the future! In 2019, AI will become your secret weapon for: Pro tip…”

Cool robot farmers — agribots in the field

“The dashboard tells you the weeds are there. The robot pulls the weed. Guess which one the farmer is going to pay for.”