Tutorials Intermediate
Kimi K3 Reasoning Effort: Stream Thoughts, Cut Cost
Tune Kimi K3's low/high/max reasoning effort and stream reasoning_content to control token cost.
9 min read·Kodetra Technologies
18d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Machine Learning Intermediate
TabFM: Zero-Shot Table Predictions That Beat XGBoost
Run Google's TabFM on real tabular data. No tuning, no feature engineering, one forward pass.
10 min read·Kodetra Technologies
24d ago
Tutorials Intermediate
Grok 4.5 Tool Loops: Tune Effort and Cache to Cut Cost
Build an agentic Grok 4.5 tool loop in Python: route reasoning_effort and cache to slash cost.
7 min read·Kodetra Technologies
28d ago
Tutorials Intermediate
Gemini 3.1 Pro: Tune Reasoning, Vision and Cost in Python
Control thinking_level, media_resolution and thought signatures in the Gemini 3.1 Pro API.
9 min read·Kodetra Technologies
Jun 10
Tutorials Intermediate
Claude Opus 4.8 Effort Levels: A Hands-On Python Guide
Tune token spend on Opus 4.8 with the effort parameter. Runnable Python, real I/O, real numbers.
7 min read·Kodetra Technologies
Jun 1
Tutorials Intermediate
DSPy GEPA: Auto-Optimize AI Agent Prompts
Use DSPy GEPA to auto-evolve prompts with reflection and beat hand-tuned baselines.
4 min read·Kodetra Technologies
May 23
Machine Learning Intermediate
Unsloth + Training Hub: Lightning-Fast LoRA in Production
Fine-tune 7B LLMs on one 24GB GPU with 70% less VRAM
7 min read·Kodetra Technologies
May 7
Machine Learning Intermediate
GRPO Fine-Tuning: Train Reasoning Into Small LLMs
Use GRPO to teach a 0.5B model multi-step math reasoning end to end.
9 min read·Kodetra Technologies
Apr 30
Database Advanced
PostgreSQL 18 Async I/O: Tune for 3x Faster Reads
Configure io_method, io_workers, and io_uring for big PostgreSQL read throughput gains.
9 min read·Kodetra Technologies
Apr 29