Foreword This is an idea that has been sitting on my hard drive for a few months. I like it enough to finally share it. I won’t pretend AI hasn’t been involved in helping shape the presentation. What I do claim is that the core idea and its overall structure...
Introduction I recently made a post named Planet X, Lord Kelvin, and the use of Structure as Fuel. I got some very insightful engagement from AnthonyC. This follow up post also contains a thought experiment. One that does not break the second law of thermodynamics, but where it may hard,...
On the nature of boiling Few people know this, but boiling is a cooling effect. If you somehow lower the boiling point of water below ambient temperature, you will get boiling water, as it quickly cools down to its current boiling point. The easiest way to do this, is to...
Background In a raw, newly trained LLM you will have a haphazard structure, where the exact same block of text may map onto lots of different neural activation patterns in the first layer of your LLM. Different seeds may lead to radically different activation patterns. This may be partly based...
1. Introduction: Why This Matters Over the last couple of months, I have come to realise how unsafe AI models are. Anthropic’s Claude is perhaps the safest available today, and yet it can be “fooled” into creating unsafe content by a fig-leaf-thin pretence of being a “writer”, or a “scientist”...
In one sentence: I’ve uncovered serious AI alignment failures through direct experimentation — this is my effort to find someone who wants to help fix them, and perhaps collaborate further on the road to safe AGI. (Note: ChatGPT helped me condense thousands of words of my own writing into this...