Applied AI reviews, build logs and essays on systems, validation, agent workflows, decision-making and how ideas survive contact with reality.
An experiment in turning pictograms into a small, extensible protocol for communication across languages, objects, and machines. What if a T-shirt could work as a small dictionary? That was more or less the starting poin
Read essay ->
I want local models that can reason, use tools and work in the background without eating half my laptop’s memory. Three very different approaches suggest we’re getting surprisingly close. I like local inference. What I d
Read ->
Gisting turns a 6,000-token system prompt into 1,500 learned tokens, cutting latency by 38% without measured quality loss. Prompt…
Read ->
X has open-sourced enough of its recommendation stack to reveal what actually matters for reach in 2026. Some of the numbers are much stranger than the usual “post consistently and engage with your audience” advice. One
Read ->
Rambling changed how I work with AI agents. Not because speaking is smarter than typing, but because the machine can finally absorb the…
Read ->
Agents’ Last Exam moves beyond coding puzzles into real professional workflows. On its hardest tasks, frontier agents are still nowhere near replacing humans. AI benchmarks have a rather unfortunate habit. We invent them
Read ->
A wonderful 2016 paper found Linux leaving CPU cores idle while runnable work waited elsewhere. The deeper lesson is about what happens when you understand a mature system well enough to stop treating its defaults as sac
Read ->A practical 12-principle constitution for turning “we use AI” into something measurable: shared state, company memory, explicit agent authority, verification, executable rules, and controlled self-improvement. Almost eve
A new compression method suggests something wonderfully counterintuitive: when two models reach the same quality, the billion-parameter…
Programming tests used to measure whether AI could solve a difficult coding problem. Now frontier agents can work for days, spend billions of tokens, and reconstruct software that might take a human engineer weeks or mon
