Hand-picked articles across AI, dev tools, databases, infrastructure, frontend, backend, and more.
9 results
Case study from the Strands Agents team. An Amazon ticket-labeling pipeline swapped Sonnet 4.6 for Strands Decider, a small open decision model that only picks between options, and cut cost per ticket from $0.0222 to about $0.0005.
Empirical study of Matt Pocock's /retro skill on Claude Code. Of seven evaluations where the targeted problem actually occurred, two harness changes eliminated it, one reduced it and four showed no reduction.
MIT CSAIL post showing GPT-6 Astra reading, fixing and writing neural network weights directly, with no gradients or training. One edit to 0.016% of Qwen3.5-0.8B's weights took MATH-500 from 7.9% to 48.1%.
Boris Tane's argument that traditional logging is broken for distributed systems and that "wide events" — one comprehensive, high-cardinality structured event per request per service — are the fix. Log what happened to the request, not what your code is doing.
Open protocol for autonomous agents to self-register for services without human intervention — a standardized auth.md file + HTTP endpoints replace OAuth and sign-up forms.
Thariq makes the case for HTML over Markdown as Claude Code's output format — richer visualizations, color, diagrams, and easier sharing once agents are the ones authoring and humans rarely hand-edit.