IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
94 articles
17 Aug 2026 · 4 min read
agentic coding
Qwen3.8-27B ships with reasoning effort defaulted to xhigh, and it shows: a trivial SVG request burns 22,000+ reasoning tokens and 21 minutes. A Technical Lead's guide to reasoning-effort as a hidden cost knob in agent pipelines.
Read more17 Aug 2026 · 5 min read
ai
Stripe's reported $7B+ acquisition of OpenRouter — up from a $1.3B valuation three months ago — validates the model-gateway architecture. A Technical Lead's take on when to buy a gateway, when to build one, and what this deal signals for API-routing infrastructure.
Read more14 Aug 2026 · 5 min read
agentic coding
Google's new Flash model jumped from 34.4% to 43.6% on FrontierCode 1.1 at half the price of its predecessor. A technical lead's take on when to route agentic coding work to the fast, cheap tier — and when not to.
Read more10 Aug 2026 · 5 min read
ai
Meta released Muse Glimmer on Aug 10, 2026 — an Apache 2.0, 30B agentic LLM that runs on a single consumer GPU with near-zero quality loss when quantized. Here's the real architecture, benchmarks, and when it beats calling an API.
Read more07 Aug 2026 · 5 min read
ai-agents
NVIDIA's NOOA framework collapses the complexity of AI agent frameworks into a single Python class — methods are actions, fields are state, docstrings are prompts, type annotations are contracts. Here's what it means for teams building production agents.
Read more07 Aug 2026 · 5 min read
ai-infrastructure
As of August 7, 2026, Cloudflare merged AI Gateway and Workers AI into a single control plane. One binding, one billing, unified observability across Cloudflare's managed GPUs and external providers. Here's what changed and what it means for AI infrastructure decisions.
Read more06 Aug 2026 · 6 min read
ai-cost
OpenAI just cut GPT-5.6 Luna pricing by 80% and Terra by 20%. Combined with 15% better token efficiency from speculative decoding, the cost math for AI products has fundamentally shifted. Here's how to rethink your model routing strategy and capture the savings without sacrificing quality where it matters.
Read more04 Aug 2026 · 7 min read
ai-agents
Astra cracked a decade-old Erdős conjecture and published Lean-verified proofs on GitHub for $2,000 of compute. Fields Medalist Timothy Gowers called one proof Annals-worthy. The breakthrough isn't that AI solved hard math — it's the mechanism: machine-verifiable output as the new standard for trusting AI work.
Read more29 Jul 2026 · 6 min read
ai
Anthropic used Claude Mythos Preview in a 60-hour multi-agent run to find genuine mathematical weaknesses in HAWK (a NIST post-quantum candidate) and reduced-round AES. Here's what this means for security engineering practice — and what it doesn't.
Read more
