[Being Human 2/n] Being scrappy shows we are Human in this Brave New World

A thoughtful piece on LinkedIn about #BeingHuman in this Brave New World we’re in. Take time to reject the AI. Being scrappy is a way of being seen!

This piece was about understanding why Symbolic Logic failed. It was super scrappy, rushed, and painful to write: [IA Series 5/n] The Evolution from Logic to Probability to Deep Learning: A course correction to Transformers…

I have also written more about Symbolic and Probabilistic Systems. Maybe I’ll just publish what I have…. 🤔

In terms of a contrast, I’ve just published something that was flow-quick and is scrappy in terms of it being human and I’ve not considered SEO, hooks, or CTAs. Though I think like minded people will see hooks and CTAs.

The piece is related to an intuition I have around LLMs being information stores and that #ContextIsAllYouNeed. How we use LLMs is more important than what they can do.

It was written in “three takes”, in around 6 hours standing at the computer. “three takes”?

• first I wrote the section on code implementation first,
• then realised I needed to go further back and start with the paper
• the final take was adding the problem and solution to frame where the paper fits in.

[IA Series 7/n] Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code…

It’s been a wonderful, and painful, journey for me.

#BeingHuman