Brickz's Blog

Can We Really Trust AI to Code?
Let’s turn to the big promise of large language models: code generation. The dream of specifying a computation in informal or almost informal language and still getting it done by the computer is as old as high-level programming languages themselves. The COBOL language already aimed at something like this (the idea being explicit already in the design of its ancestor, B-0 or ‘FLOW-MATIC’), although dire necessities posed by the meager

Treating LLMs as Black Boxes
As we said last time, LLMs are a bit like alien artefacts, black boxes whose function and proper use we are investigating in ways not dissimilar to the way our stone age ancestors would puzzle over a plumber’s toolbox. The situation is familiar for those who have had to deal with any but the most trivial machine learning methods; most of those resist any attempt to extract the actual rules

Beyond the Hype
What Huge Context Windows Actually Mean Announcements of large language models featuring huge context windows – possibly of one million or more tokens – pop up somewhat regularly by now, and usually spur a veritable avalanche of hypotheses as to in what area are they expected to prove useful. The current iteration centres around Gemini 2.0 Flash, and the idea seems to be that it will revolutionize the RAG architecture.

LLMs Unveiled
Separating Fact from Fiction in AI Technology It would seem that the perception of what current parlance calls ‘AI’ could stand some improvement. We often find indirect information about how that mythical being, the Average Computer User (henceforth ACU), sees the currently fashionable chatbots. The following assumptions hold: None of this is entirely false, but if we had to round it to the nearest boolean value, that value would be