Blog Kami

The same requests.get was harmless in a def endpoint and froze the server in an async def one: an unrelated endpoint went from 1.6 ms to 34 seconds. Plus FastAPI's 40-thread cliff, why asyncio.to_thread barely helps CPU work, and a watchdog that names the blocking line.

Earlier this month, a developer in Atlanta got fed up with Adobe's cancellation fees. So he used...

There is a special kind of confidence that comes from an AI development environment that just works....

Fourteen Apache-2.0 and MIT open-weight models that fit one TPU v5e chip, served one after another through vLLM on the same pinned image and scored on GSM8K and BFCL against Gemma 4 E2B. Qwen3-4B matches Gemma's accuracy at 0.57x its output, SmolLM3-3B and Granite 3.3 2B match it on tool calls, and Gemma keeps the lead on long prompts.

Every "7 local models that replace Claude Code" list opens the same way: a table of SWE-bench scores,...

One right answer is not the same as a good sequence of decisions. eSlams is building a public stadium...

You’ve read way too many versions of this paragraph already. Probably even this week: “In today’s...

What I Built SoloDesk AI is a privacy-first, zero-marginal-cost financial copilot and invoice...

Beyond chat with llamadart · Part 2 Llama Village, where five llamas share a world without sharing...