I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.
Loop Engineering - by Addy Osmani - ElevateCataloging common LLM failure patterns ('smells') surfaces pitfalls that loop-engineering designs must guard against when removing humans from the prompt loop.
Related
Humanising LLM Outputs is DumbBoth critique problematic patterns in LLM outputs — 'humanising' as wrong abstraction vs. 'smells' as anti-patterns; both focus on diagnosing and fixing undesirable LLM behavior rather than accepting it
8 Myths of Software Development with AIBoth critically examine problematic patterns and misconceptions in AI-assisted software development, offering corrective perspectives for practitioners
Challenged by
LLMs reward expertise'Various LLM Smells' catalogs failure modes of LLMs that persist regardless of user expertise, partially challenging the claim that domain expertise alone determines effectiveness
Supported by
Pi, Minimal and PerformantPi's design philosophy (lean prompts, few tools) is a practical remedy for the LLM 'smells' caused by over-engineered prompts and excessive tool sprawl
mattwood.fyi