Machine Learning Advanced
Detect AI Text: Build a SynthID Watermark Scorer
Score any text for Claude-style SynthID watermarks in Python, with real measured g-values.
12 min read·Kodetra Technologies
YesterdayGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning 
Tutorials Intermediate
AWS Dogwood: Temporal Guardrails for Agent Tool Calls
Gate agent tool calls on what happened before, not one request at a time.
11 min read·Kodetra Technologies
2d ago
Tutorials Intermediate
Migrate to Gemini 3.7 Flash: The minimal Thinking Trap
Preflight your configs for gemini-3.7-flash: 5 breaking changes, a validator, real cost math.
12 min read·Kodetra Technologies
2d ago
Tutorials Intermediate
Guaranteed JSON From Claude: Structured Outputs in Python
Force Claude to return schema-valid JSON every time, no parsing errors and no retries.
9 min read·Kodetra Technologies
23d ago
Tutorials Intermediate
Kimi K3 Dynamic Tool Loading: Inject Tools On Demand
Load tools just-in-time in Kimi K3's agent loop to shrink prompts and sharpen tool choice.
8 min read·Kodetra Technologies
Jul 20
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
Jul 14
Machine Learning Advanced
Verifiers v1: Train Agents Past the Context Window
Ship a taskset, swap any harness, and turn compacted rollouts into real RL training samples.
13 min read·Kodetra Technologies
Jul 14
Tutorials Intermediate
Live X Search Agent: Real-Time Trend Tracking With Grok
Use Grok 4.5's server-side X Search on the xAI API to build a cited, real-time trend agent.
10 min read·Kodetra Technologies
Jul 10
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
Jun 19
Machine Learning Intermediate
Build a Deployment Simulation Eval to Catch Model Drift
Replay real conversations through a candidate model to predict misbehavior before you ship.
11 min read·Kodetra Technologies
Jun 18
Tutorials Intermediate
Kimi K2.7 Code: Build a Multi-File Refactor Agent
Drive Moonshot's open-weight coding model through a real tool-calling loop in Python.
9 min read·Kodetra Technologies
Jun 16
Tutorials Intermediate
MiniMax M3: Master 1M-Token Long Context With MSA
MiniMax M3 hands-on: MSA sparse attention plus real 1M-token long context, with runnable Python.
10 min read·Kodetra Technologies
Jun 12Page 1 of 2