Dan Shiebler

From One Agent to Many The math behind multi-agent ensembles is simpler than you think – and it tells you exactly when adding agents helps.

No generative AI here - just good old-fashioned statistics.

Every system has properties that define its usefulness.

Ever had a complex Python function you wanted to quickly host as an API?

When building systems to detect cyberattacks or fraud, technical expertise alone isn’t enough.

Software engineering is changing.

Asynchronous communication through tools like Email, Slack, and Docs has become central to how teams work.

Suppose you are a payment processor handling thousands or millions of payments every day.

Sloppy analytics can lend false confidence to bad decisions.

The CEO needs to increase company margins.

I’ve spent a lot of time leading large and small engineering teams over the last decade.

Generative large language models (LLMs) like ChatGPT are like wild beasts.

Generative large language models (LLMs) like ChatGPT will revolutionize the way we approach complex problems.

ML models are collaboration bottlenecks.

One of the hallmarks of a great engineer is the ability to execute.

A common problem in machine learning is “use this function defined over this small set to generate predictions over that larger set.”

A boxer who only punches a bag will fail in the ring, and an ML model that only learns with clean data will fail in production.

Many real world problems can be framed as regression: use a collection of features \(X\) to predict a real-valued quantity \(y\).

Introduction Many prediction problems can be framed as “given the knowledge that this sample belongs to categories \(A,B,C,\cdots,D\), predict something about this sample.”

This post is part three in a three part series on the challenges of improving a production machine learning system.