IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
94 articles
03 Apr 2026 · 6 min read
2026
OpenAI just extended the Responses API with a shell tool, hosted container workspace, context compaction, and reusable agent skills. Here's what this means for teams building real agentic workflows — with hands-on examples.
Read more03 Apr 2026 · 6 min read
2026
Alibaba just released its third proprietary model in days. Google's Gemini Flash-Lite costs $0.25 per million tokens. NVIDIA's Nemotron runs 2.2x faster than GPT-OSS-120B. The LLM cost war has arrived — here's what it means for architects choosing AI infrastructure in 2026.
Read more01 Apr 2026 · 6 min read
agentic-ai
GPT-5.4 crossed human performance on desktop tasks. With a hosted shell, 1M context window, and native compaction, the era of AI as an autonomous coworker is finally here — and the implications for developers are profound.
Read more28 Mar 2026 · 6 min read
ai
GPT-4 level AI cost $30/M tokens in 2023. Today it's under $1. Here's the technical architecture that lets you capture 90%+ of that savings without sacrificing quality.
Read more27 Mar 2026 · 5 min read
ai
Deep dive into Gemini 3.1 Pro's practical developer features — 77.1% ARC-AGI-2, dynamic thinking API, 1M token context, and what these benchmarks actually mean when building production AI systems.
Read more26 Mar 2026 · 6 min read
ai
Beyond benchmarks — a real comparison of DeepSeek V3.2 and Gemini 3 Pro for production developer workflows. Cost, code quality, context window, multimodal capabilities, and when to use which.
Read more25 Mar 2026 · 6 min read
cost-optimization
Mistral Large 3's MoE architecture delivers 92% of GPT-5.2's performance at 15% of the cost. As a technical lead who has run open-source LLMs in production, here's where it works and where it fails.
Read more24 Mar 2026 · 5 min read
ai
Claude Opus 4.6, GPT-5.4 Thinking, and Gemini 3.1 Pro all shipped within the same month. Here's a practical guide to choosing the right model for your team — based on real benchmarks and production patterns, not marketing slides.
Read more24 Mar 2026 · 6 min read
ai
Mistral's Devstral 2 scores 72.2% on SWE-bench, ships under MIT license, and costs up to 7x less than Claude Sonnet. Here's how it works, when to use it, and whether open-source agentic coding is finally production-ready.
Read more
