Black Sheep Code

Articles tagged "ai":

What's good for humans is good for AI and what's good for AI is good for AI

Published:

The same engineering practises that allow an AI to make effective use of a codebase, are the ones that allow humans to make effective use of the code base

AI and the carve-out of middle class power

Published:

How replacing the middle class with AI could shift power toward the owners of capital.

An inversion of information discovery

Published:

Our information discovery starts at a high level and then digs in. In the AI world, it might be better to have AI do deep discovery and then summarize.

An AI-generated blindfold

Published:

Increasingly, I'm finding it hard to hard to get a sense of human consensus on a topic from the internet

Human comprehension is still the bottleneck

Published:

All this talk about how AI can build a whole whatever with $120 of credits and a day is beside the point - the bottleneck is how fast we can understand things

Does this tool exist? A tool for comparing/testing the difference between LLM harnesses, models and prompts

Published:

All the talk in the world about certain prompting techniques, models, or workflow strategies isn't very useful unless you can actually measure it

Where are the prompts to stop humans going off the rails?

Published:

Humans are just as finicky as AI

The case for adding a 'this file was generated by AI' header

Published:

It helps not gaslight anyone reading the code

Psychological pitfalls of using artificial intelligence - a heightened sense of urgency

Published:

AI can provide a lot of content very quickly, and we can feel the need to match its pace.

Reasons to be a token miser

Published:

There is a school of thought that says 'Just throw money at the problem' - here's why you should be constantly optimising your token usage.

Agentic AI - yak shaving on steroids

Published:

The prospect of having agentic AI do all the real work means that we now focus on tuning the AI, not delivering the work.