Machine Learning Intermediate
Framing Gap Eval: Catch Covert Underperformance in LLMs
Build a paired-framing eval with hidden tests to catch quiet sandbagging, per OpenAI's Astra report.
12 min read·Kodetra Technologies
2d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning 
Machine Learning Intermediate
Small CNN vs Frontier LLMs: Run a Fair Head-to-Head
Fine-tune Inception v3, query a vision LLM, and compare both at a matched threshold.
11 min read·Kodetra Technologies
12d ago
Tutorials Intermediate
Reflection Beam: Get Agent-Ready Before the Weights Drop
Build an effort-routing tool-loop client for Beam's OpenAI-compatible API and size the self-host bill.
8 min read·Kodetra Technologies
Oct 6
Tutorials Intermediate
OpenAI Agents API: Run a Data Audit in a Cloud Sandbox
Run a durable Codex-powered agent in OpenAI's hosted sandbox with a custom tool and file outputs.
14 min read·Kodetra Technologies
Oct 1
Tutorials Advanced
OpenAI Multi-Agent Beta: Ship an Agent Tree in Python
Enable multi_agent on the Responses API, trace every subagent, and dodge the hosted-call trap.
14 min read·Kodetra Technologies
Sep 9
Tutorials Intermediate
OpenViking: Agent Memory You Can ls and grep
Build browsable, self-evolving agent memory with OpenViking's viking:// filesystem in Python.
11 min read·Kodetra Technologies
Sep 1
Tutorials Intermediate
MCP Auth Without DCR: Ship a CIMD Client Document
MCP 2026-07-28 deprecates DCR. Host a metadata document and let its URL be your client_id.
16 min read·Kodetra Technologies
Aug 25
Tutorials Intermediate
Build a Self-Verifying Agent With Grok 4.6 in Python
Grok 4.6 self-verifies during long agent runs. Build a Python coding agent that checks its own work.
9 min read·Kodetra Technologies
Aug 13
Tutorials Intermediate
Build a Self-Healing Agent With Local Muse Glimmer
Meta's new 30B Muse Glimmer runs a local tool-calling agent that recovers when tools fail.
9 min read·Kodetra Technologies
Aug 10
Tutorials Advanced
Self-Host Kimi K3 Open Weights With vLLM
Run Moonshot's 2.8T open-weight model on your own GPUs with vLLM and MXFP4.
9 min read·Kodetra Technologies
Jul 27
Tutorials Intermediate
Muse Spark 1.1: Drop-In Agent, Self-Managed Context
Point the OpenAI SDK at Meta's agent model, add tools, let it self-manage a 1M-token context.
10 min read·Kodetra Technologies
Jul 17
Tutorials Intermediate
Hermes Agent: Teach a Local LLM to Write Its Own Skills
Install Nous Research's self-improving agent, run it on a local model, and build a reusable skill.
11 min read·Kodetra Technologies
Jul 2Page 1 of 2