DeepSeek V4.1 Flash: Release Status, Specs, Pricing, and Migration
DeepSeek V4.1 Flash is now the production Flash model. Verify its model ID, 1M context, vision support, peak pricing, retired aliases, and…
Judy3 min read
Judy
10 articles by Judy.
Codex Harness Open Source — OpenAI's Agent Runtime
OpenAI's Codex harness is open on GitHub: exec, SDK, and app-server. What's in the agent loop, what's not open, and how it compares to…
Judy12 min read
DeepSeek Agent Function Calling: Schemas, Loops, and Safety
Learn DeepSeek function calling for agents: tool schemas, strict mode, parallel tool calls, thinking mode, MCP, and production repair…
Judy11 min read
DeepSeek V4 Pro 0813 — The Quiet GA and What It Actually Changes
DeepSeek V4 Pro 0813 went GA with no announcement. Specs, claimed agent benchmarks, the pricing window before the hike, and how it stacks…
Judy13 min read
What Is Grok Bot? xAI's Cloud-Computer Agent Explained
Grok Bot explained: how its always-on cloud computer, routines, multi-bot coordination, X integration, access model, and approval…
Judy8 min read
How to Build a DeepSeek Agent: From API Key to Your First Agent
Step-by-step guide to building a DeepSeek Agent with V4 Pro and V4 Flash. Covers API setup, model selection, tool calling, the agent loop,…
Judy2 min read
How to Use Obsidian with an AI Agent Safely
Use an AI agent with Obsidian without handing over your whole knowledge base. This practical workflow covers access scope, read-only…
Judy6 min read
World Cup 2026 Bracket: Complete Knockout Results and Final Path
The completed 2026 World Cup bracket from the Round of 32 to the final: every knockout result, Spain's title path, bracket rules, and…
Judy4 min read
GPT-5.6 and Floatboat: Support Status, Model Tiers, and What Users Can Select
A factual guide to GPT-5.6 Sol, Terra, and Luna in relation to Floatboat: which models are configured below the picker, what OpenAI offers,…
Judy4 min read
GPT-5.6 Sol, Terra, and Luna: Current Prices and Which Tier to Use
Compare GPT-5.6 Sol, Terra, and Luna using current API prices, context limits, reasoning modes, tool support, and a workload-based model…
Judy3 min read
/blog/author/judy
Questions Explored in Judy’s Articles
Explore questions covered in the articles listed here. Each answer links to its original explanation and publication context.
Is DeepSeek V4.1 Flash still a beta?
No. It is the production Flash model served as deepseek-flash.
Source: DeepSeek V4.1 Flash: Release Status, Specs, Pricing, and Migration
What happened to the expiring beta ID?
It expired and should not be used in production configuration.
Source: DeepSeek V4.1 Flash: Release Status, Specs, Pricing, and Migration
What is Codex Harness?
It is the open agent runtime and integration layer behind Codex workflows.
Source: Codex Harness Open Source — OpenAI's Agent Runtime
Which components are open?
OpenAI names Codex CLI, app-server, and the official SDK as open-source components.
Source: Codex Harness Open Source — OpenAI's Agent Runtime
Do I need an Obsidian plugin to use an AI agent?
No. A file-capable agent can work with an authorized vault folder directly. Use an in-vault plugin when you want AI inside Obsidian, or the official CLI for repeatable Obsidian commands.
Source: How to Use Obsidian with an AI Agent Safely
What is the safest first AI task for a vault?
Start read-only: ask for an inventory, a source-linked summary, or unanswered questions from one project folder. Confirm the scope before allowing a small write.
Source: How to Use Obsidian with an AI Agent Safely