Coding agents accelerate decision fatigue, leading to accepting decisions due to lack of energy to push back or think of alternative approaches. Slow down.

#AI #ClaudeCode #DecisionFatigue

Build *your* mental model through real practice and study, not only what the LLM tells you. You can't build muscles by watching someone else work out. It's the same with using AI.

#AI #TrainYourBrain

Please do not implicitly trust anything generated by an LLM. Confident framing often appears indistinguishable from verified claim.

LLMs are game changers for learning, researching, and experimenting. They will boost your productivity. But approach your work in small iterations, and rely on primary (or well-regarded secondary) sources.

In the world of software, instrumentation is a primary source. Observability can help shed light on reality.

#AI #Observability #ContextEngineering

Confident framing indistinguishable from verified claim, until instrumentation arrives and breaks it.

#AI #Agents

"This is a massive paradigm shift. The internet replaced a lot of trips to the library. Agents are starting to replace trips to the internet."

"Using an agent to search the internet feels as easy as slicing and dicing with SQL. Exactly the kind of thing these agents are great at. It feels as natural as creating digital art from a diverse palette of colors and tools, applied to search."

https://www.linkedin.com/pulse/i-asked-ai-agent-find-movie-showtimes-worked-too-well-sujan-kapadia-ecoae/?trackingId=IG%2Bm%2FT54gLNpbjd8m1sVwA%3D%3D

playwright is one of the unsung heroes of agentic workflows. I heavily rely on it. In addition to the obvious DOM inspection capabilities, the fact that the console and network can be inspected is a game changer for debugging. watching an agent get rapid feedback or do live TDD is one of the most satisfying things ever.

#playwright #ai #agents