English · 中文

A First Look at Gemini 3.7 Flash: A Workhorse for Coding and Agents

Aug 15, 2026

Evaluate Gemini 3.7 Flash for coding, tools, multimodal input, and thinking levels with a reproducible adoption gate.

Building a Tool-Using Agent with Qwen3: MCP, Thinking Budgets, and Recovery

Aug 10, 2026

Use Qwen3 and Qwen-Agent with mock tools to design MCP registration, bounded thinking, idempotent execution, and recoverable failures.

A First Look at Claude Opus 5: Stronger Long-Running Agents Need Better Verification

Aug 3, 2026

Turn Claude Opus 5 capability claims into a long-running agent verification plan with checkpoints, tool evidence, budgets, and takeover.

A GPT-5.6 Responses API Tutorial: Reasoning Levels, Tools, and Cost Baselines

Jul 24, 2026

Construct an offline GPT-5.6 Responses API workflow with explicit reasoning, narrow tools, usage capture, and a recorded cost baseline.

GPT-5.6 Sol, Terra, and Luna: How to Choose the New Tiers

Jul 13, 2026

Choose among GPT-5.6 Sol, Terra, and Luna with task risk, quality, latency, and cost evaluations instead of treating the tiers as simple sizes.

  • « Prev
  • Page 3 of 14
  • Next »
Portrait of Lukes Lu

Lukes Lu

Software Developer

  • lukes.lu@yahoo.com
  • github.com/ilukes
  • @lupingui
  • Home
  • About
  • Keywords →
    • SwiftUI
    • OpenAI
    • Responses API
    • cancellation
    • iOS 26 beta
    • reasoning effort
    • AI Agent
    • Codex

©2026 All rights reserved. Made with Jekyll and ♥