Tutorials Intermediate
Claude Sonnet 5: Adaptive Thinking and Effort in Python
Master Sonnet 5's on-by-default thinking and the effort knob to cut cost and latency.
9 min read·Kodetra Technologies
13d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Mercury 2 dLLM: Reasoning at 1000 Tokens Per Second
Build real-time agents on the first reasoning diffusion LLM: OpenAI-compatible, 1000 tok/s.
8 min read·Kodetra Technologies
26d ago
Tutorials Intermediate
Claude Opus 4.8 Fast Mode: 2.5x Faster Output in Python
Use speed:"fast" on Claude Opus 4.8 for up to 2.5x faster output, with a safe rate-limit fallback.
9 min read·Kodetra Technologies
Jun 10
Tutorials Intermediate
CodeAct + Hyperlight: One Code Block, Dozens of Tool Calls
Collapse agent tool-call loops into one sandboxed Python program and cut latency in half.
10 min read·Kodetra Technologies
Jun 4
System Design Intermediate
Hedged Requests: Tame P99 Tail Latency at Scale
Send a backup when the first call is slow. Cut P99 tail latency without overloading services.
9 min read·Kodetra Technologies
May 20