Machine Learning Intermediate
Inkling 2 Small: Tune Reasoning Effort, Pay Less Per Answer
Sweep Inkling 2 Small's effort dial through Tinker's OpenAI endpoint, then route by cost.
10 min read·Kodetra Technologies
TodayGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning 
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 ago
Machine Learning Intermediate
Shutdown Test: Will Your Model Obey a Stop Order?
Rebuild the shutdown test behind DeepSeek's 39% headline and run it on your own agent.
11 min read·Kodetra Technologies
12d ago
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
OpenAI 12h Cache: Split Agent Prompts Into Two TTLs
Use OpenAI's new 12-hour prompt cache for stable context, 30 minutes for the rest.
9 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
Agensh: Build a Leaderless Agent Team in Python
Microsoft's 1,024-agent harness explained, plus a runnable claim-verify-merge board.
12 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
GPT-6.1 Terra Invoice Reader: Image to Ledger in Python
Read invoice images with gpt-6.1-terra, sweep reasoning effort, escalate only when math fails.
13 min read·Kodetra Technologies
13d ago
Tutorials Intermediate
Kimi K3.1 Pro: Claim-Level Hallucination Check in Python
Moonshot claims 8.3% hallucination on K3.1 Pro. Measure the real rate on your own documents.
10 min read·Kodetra Technologies
16d ago
Tutorials Intermediate
Claude API 2026-10-21: Build a Migration Scanner in Python
Claude SDK 2.0 and API 2026-10-21 break old code. Scan for every 400 and TypeError first.
14 min read·Kodetra Technologies
17d ago
Tutorials Intermediate
DeepSeek Flash-1017: Benchmark Cost per Solved Task
Measure what DeepSeek V4.1-Flash-1017 really costs per solved task at each reasoning effort.
12 min read·Kodetra Technologies
18d ago
Tutorials Intermediate
Gemini 4 Argon Long Decode: 200K Tokens, One Request
Use Argon's background long decode to generate 1M tokens of output, with cost math.
9 min read·Kodetra Technologies
26d ago
Tutorials Intermediate
Preserved Thinking: Build a Prefix-Drift Guard in Python
Claude now 400s agents that edit history. Catch the edit before the API does.
13 min read·Kodetra Technologies
27d agoPage 1 of 15