Notes on data, AI, IT
and security
No marketing fog. The way I think about real problems with founders and managers.
LLM context windows: what the limit means for business applications
Why the context window constraint in language models is not a technical footnote but an architectural decision that determines what can actually be built.
AI in 2023: what actually changed and what is still open
A mid-November account of what the year delivered in practical terms - not a hype recap but an honest read of where things moved and where the gaps remain.
DevDay, long context, and the tooling shift toward LLM production systems
What OpenAI's DevDay announcements mean for companies thinking about moving from LLM pilots to working production systems.
LLM operational economics: how to model costs before you scale
Why token costs for language models need to be modelled in advance, and how to avoid an unexpected invoice when load grows.
Fine-tuning GPT-3.5: when it makes sense and when it does not
OpenAI opened fine-tuning for GPT-3.5 Turbo in August 2023. Here is a practical read on the use cases where it delivers and the ones where prompt engineering is still the right call.
Llama 2 and open weights: what it means for enterprise
A look at why larger organisations should pay attention to open-weight language models, and where the real boundary between opportunity and illusion lies.
From pilot to product: the gap that breaks AI projects
A language model works beautifully in a demo - and falls apart in real use. I look at where the gap is and how to bridge it.
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.