Notes on data, AI, IT
and security
No marketing fog. The way I think about real problems with founders and managers.
OpenAI plugins: what the announcement actually means for builders
OpenAI opened plugin access to developers this week. Here is a calm reading of what the architecture implies - and what questions to ask before building on it.
Prompt engineering: the patterns that actually matter in practice
A grounded overview of the prompt techniques that produce reliable results, and the ones that sound sophisticated but do not hold up in production.
GPT-4 and a new conversation about quality, multimodality and the cost of errors
The release of GPT-4 changes not only what language models can do but the conversation about when AI is acceptable in production systems. I look at three key shifts.
RAG: how retrieval-augmented generation actually works
Before building a chatbot over your own documents, it helps to understand what RAG does, what it does not do, and where the failure points are.
NIST AI RMF 1.0: trustworthy AI gets a practical framework
In January 2023 NIST published the first version of its AI Risk Management Framework. I look at what it means for companies already using or planning to adopt AI.
ChatGPT: the consumer interface to AI goes mass market
What the launch of ChatGPT means for companies and managers - not technologically, but in terms of how expectations around automation will change.
Stable Diffusion and open generative graphics as a market factor
What the public release of Stable Diffusion means for companies that work with visual content, branding, and creative processes.
GitHub Copilot: what changes for development teams and what a manager should think about
GitHub Copilot launched publicly. A look at what this changes for engineering teams and what questions managers should be asking.
DALL-E 2 and the new visual productivity
OpenAI unveiled DALL-E 2. A look at what changes for business - not for artists, but for companies that work with visual content every day.
GPT-3 in the API: what a founder should do with it
OpenAI opened GPT-3 access through its API. A clear-headed look at what changes for business and where to slow down.
The gap between experiment and production: why ML models never reach work
Most ML projects show good results in experiments and perform poorly in production. I look at why this happens.
When a good model goes bad: drift, detection, and business cost
A model that passed every test at launch can quietly degrade over months. Understanding why helps you decide how much monitoring is worth the investment.