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
3d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
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
5d 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
13d ago
Tutorials Intermediate
Haiku 5.5 Triage: Measure Effort, Then Route by Cost
Benchmark Haiku 5.5 effort levels on your own tickets, then route cheap-first.
10 min read·Kodetra Technologies
19d ago
Tutorials Intermediate
Codex Security CLI: Gate PRs on High Severity
Scan a PR diff with OpenAI's Codex Security, cap the spend, and fail CI on high-severity bugs.
13 min read·Kodetra Technologies
26d ago
Tutorials Intermediate
Sonnet 5.5 Drops tool_choice: Build a Strict Tool Router
Forced tool use now 400s on Claude Sonnet 5.5. Replace it with strict tools and a retry guard.
9 min read·Kodetra Technologies
28d ago
Tutorials Intermediate
Claude Code Projects: Retire an API Across 3 Repos
Set up Claude Code's new Projects beta to run coordinated, parallel AI coding threads across repos.
11 min read·Kodetra Technologies
Sep 26
Tutorials Intermediate
Gemini 3.8 Live: Build a Multilingual Voice Agent
Build a real-time voice agent with Gemini 3.8 Live Extended Thinking.
10 min read·Kodetra Technologies
Sep 25
Tutorials Intermediate
Opus 5.5 Progress Updates: Stop Silent Agent Turns
Opus 5.5 moved agent narration into thinking blocks. Stream it back with display updates and nudges.
15 min read·Kodetra Technologies
Sep 24
Tutorials Advanced
Opus 5.5 Background Compaction: Agents That Never Stall
Summarize long Claude Opus 5.5 sessions in a background thread and swap the result in, no pause.
15 min read·Kodetra Technologies
Sep 23
Tutorials Intermediate
Opus 5.5 Upgrade: Fix 4 Breaking Changes Before They 400
Opus 5.5 is 20% cheaper, but old thinking, tool_choice and computer-use code now fails. Fix it.
15 min read·Kodetra Technologies
Sep 23
Tutorials Intermediate
Qwen3.8-Flash-Next: Preserved Thinking, Cheaper Agents
Qwen keeps reasoning across every turn by default. Exploit it, or pay for it.
11 min read·Kodetra Technologies
Aug 27Page 1 of 6