Always Switching: The Hidden Cost of AI-Assisted Momentum
AI introduced a new rhythm in which workers managed several active threads…
Found in the Wild (4)
Interesting snippets I stumble upon while browsing the internet. A quote, a take, a revelation, a throwaway line that turns out to be gold. Something that made me pause and think "huh, that's worth sharing."
Under this section, you will find my collection of raw quotes - presented as-is, with just enough context to point you toward the source, and a nudge to look closer.
Strategic Ignorance in the Age of Claude Code
Funny and relatable, at least for me: Source: X.com
Understanding LLM Size, Weights, Parameters, Quantization, KV Cache & Inference Memory
How much RAM do you need to run a 30 billion parameter model? Why are there multiple versions of the same model at different file sizes? What does "8-bit quantization" actually mean, and how does it affect performance and/or precision? If you're running language models locally or planning to, understanding the relationship between parameters, weights, quantization, and memory is essential.
Summarization in Claude Code to reduce Prompt Injection risk
Boris Cherny, creator of Claude Code posted on X: Summarization is one…
