Thoughts
-
Agentic Engineering and the Art of Bullshit
Treating LLMs as sophisticated bullshit generators and designing systems that harness them effectively
-
Endless Method Definitions in Ruby
Today I Learnt - Episode #127
-
Coherence and Cogency
LLMs are coherence machines, not truth-checkers
-
LLMs are cats, not dogs
Why you need to understand them in order to herd them
-
The Intelligence of Ignorance
Why Narrower LLMs Outperform "God Models"
-
The Software Paradox
Code is both an asset and a liability
-
Disposable Software
Part 2 on the industrialisation of software development
-
Disposable Software
Part 1 on the industrialisation of software development
-
DIY vs USE
How GenAI alters the Not-Invented-Here dynamic
-
Context and Constraints
How restricted context windows help us build better agentic systems
-
Not Even Wrong
How restricted context windows help us build better agentic systems
-
Stochastic Parrots and Thinking Machines
Why metaphors matter when talking about AI
-
Go slow to go fast
Moving fast doesn't need to break things
-
The Truth Problem
LLMs can't lie because they don't know the truth