Distributed computing with Ray, from one core to 64
A client bought a 64-core Threadripper and their script still ran on one core for an hour. Ray brought it down to about two minutes, with less code than the multiprocessing version I tried first.
Category: AI
Agentic AI workflows that survive a failed API call
A client’s research pipeline kept hallucinating specs until we stopped writing one giant prompt. Notes on using IntelliNode’s VibeFlow to compile intent into a task graph, plus the code we run in production.
A tabular foundation model beats XGBoost on 800 rows
Predicting lead conversion from 800 WooCommerce rows, where XGBoost just memorized the noise. Why TabPFN and in-context learning made a better baseline than another afternoon of hyperparameter tuning.
Why I swapped mega-prompts for a custom AI assistant
I spent hours refining a mega-prompt and still got different output every session. Here is why that logic moved into a custom AI assistant, how the MATCH framework structures one, and when a private local session is the better call.
The YOLOv1 loss function, one term at a time
A client’s detector found the gearboxes and ignored the bolts, and the problem was the loss function rather than the dataset. Here is how the YOLOv1 loss splits into five terms, why width and height get a square root, and what the lambdas are for.
Prompt engineering vs RAG: the resume that lied
A friend’s AI resume draft claimed an Azure certification he never had. Three hours of prompt tweaking did not stop it, but indexing his verified work history did, and a grounded mini model beat an ungrounded larger one.
Why I moved a client’s agent to the NeMo Agent Toolkit
A client’s weekend-built AI agent fell apart the moment real users touched it. Here is what the NeMo Agent Toolkit handled for us that my own custom wrapper could not: YAML config, grounded tools, and a server you get for free.
Effective AI programming is a context problem
An AI coding agent invented table names on a 50k SKU WooCommerce sync until I wrote the schema down for it. Here are the context files I now keep in every project, and why decisions made in meetings need to end up in the repo too.
Turning dead user research into virtual personas
A 60-page research PDF nobody ever opened became a set of virtual personas the team could actually question mid-sprint. Here is the setup, the kind of data you need to feed it, and the mistake that makes the whole thing useless.
The actor-critic method and the bugs that stall it
REINFORCE was too slow for a warehouse path-finding bot, so I switched to the actor-critic method and hit three problems on the way: an undetached TD target, snapshot rewards the agent gamed, and a gamma that erased the payoff.