{
  "articles": [
    {
      "url": "/en/2026/08/23/agent-engineering-from-claude-code/",
      "title": "Three Claude Code implementations: an agent engineering notebook",
      "excerpt": "Agent engineering notes drawn from three implementations. CoreCoder is a minimal implementation written by hand in Python, Claude Code is the production implementation, and learn-claude-code is the teaching implementation. Coverage spans the Agent Loop's transition condition and interrupt repair, tool definitions and file-editing strategy, context injection and three tiers of compression, the long-lived state of QueryEngine, parallel tools and sub-agents, the Hook and Task extension points, multi-agent collaboration, memory / MCP / background tasks / scheduled tasks, and the security defenses around paths and commands.",
      "tags": [
        "Agent",
        "Claude Code",
        "source reading",
        "engineering practice"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-08-23"
    },
    {
      "url": "/en/2026/04/04/transformer-learning-notes/",
      "title": "Transformer learning notes: from the overall architecture to multi-head attention",
      "excerpt": "Transformer study notes ordered whole-first and then part-by-part: the data flow through the encoder and the decoder; the three questions to answer before learning large models (neural networks, attention, what PyTorch is made of); what Token, the word embedding matrix, and positional encoding each solve; the meaning of Q, K, and V, why the Q·K dot product stands for relevance, and why the dot product is divided by the square root of the dimension before softmax; the difference between self-attention and cross-attention, and why cross-attention needs no mask; training predicts several tokens in parallel while inference generates one token at a time, which is why a causal mask is needed to prevent peeking, implemented by setting later positions to negative infinity so that softmax turns them into 0; the definitions of the feed-forward network, multi-head attention, and layer normalization, including how layer norm and batch norm differ in which dimension they normalize over.",
      "tags": [
        "Transformer",
        "Deep learning",
        "Attention mechanism",
        "Study notes"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-04-04"
    }
  ],
  "notes": [
    {
      "url": "/en/notes/from-csdn/",
      "title": "From CSDN to a site of my own",
      "excerpt": "A summary of the CSDN period — Python, NumPy/pandas, data analysis, visualization, and a few competition projects first; then transformers, LLMs, and agents (tool calling, the agent loop, multi-agent setups, prompt / context / harness, Claude Code, prompt-injection defences, agent checkpoints). From September 2026 the blog lives on my own site; the old CSDN posts stay up but are no longer updated.",
      "tags": [
        "notes",
        "writing"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-09-24"
    },
    {
      "url": "/en/notes/interview-questions/",
      "title": "Two or three small-company interviews: eight questions on agents and LLMs",
      "excerpt": "A debrief of two or three interviews at small companies. The projects were one agent and one LLM, and the questions landed in the same two places — why GQA works (MHA's dimensional expressiveness, MQA's KV cache, GQA as the middle ground), three layers of prompt-injection defence (model / agent / permissions), VRAM and CPU-and-memory contention with a hundred-plus concurrent users, what to do when a sub-agent gets stuck (timeouts and a scheduler), which fields a trace should observe and the ten questions it must answer, recovering information lost in summary compression, what a high-risk approval prompt has to show, and saving checkpoints by event rather than per step.",
      "tags": [
        "notes",
        "interviews",
        "Agent",
        "LLM"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-08-21"
    }
  ],
  "answers": [
    {
      "url": "/en/answers/agent-ready/",
      "q": "How can AI agents read this site?",
      "a": "The build generates llms.txt and llms-full.txt indexes, a Markdown mirror per page, JSON endpoints for articles, profile, and search, plus an OpenAPI description — so agents can cite material without parsing page layouts.",
      "full": "**One corpus, two read paths: pages for people and interfaces for machines.** The index is [llms.txt](/en/llms.txt), and the full corpus sits at [llms-full.txt](/en/llms-full.txt).\n\nArticles, notes, and answers each have a Markdown mirror and a JSON endpoint — /api/articles.json, /api/profile.json, /api/search-index.json — with field descriptions in [openapi.json](/openapi.json) and a sitemap at /sitemap-index.xml. The Markdown mirror is the source text that was published, so citations do not drift from the rendered page.\n\nAsking on this site runs in three layers: curated answers, full-text retrieval, and live AI answers (see \"How do search and asking work here?\"). The live answers come from a same-origin worker that retrieves this site's public content before generating a source-cited, single-turn answer, without long-term memory."
    },
    {
      "url": "/en/answers/collaborate/",
      "q": "How can I collaborate with HYD?",
      "a": "Email HYDhyd0505@gmail.com, or open an issue or a pull request as HYDtomako on GitHub — AI agent practice, open-source collaboration, and publishing setups are all welcome.",
      "full": "**The fastest route is email: HYDhyd0505@gmail.com.** You can also open an issue or a pull request on GitHub under HYDtomako, or reach out on QQ at 2804956879.\n\nWorth talking about: AI agent practice — tool calling, long-term memory, multi-agent collaboration; splitting work and reviewing code on open-source projects; and personal sites and publishing. What exists today is listed on the [projects page](/en/projects/), so if something there looks worth doing together, just say so.\n\nStill a student, so replies may take a while, but every message gets read."
    },
    {
      "url": "/en/answers/live-ask/",
      "q": "How do search and asking work here?",
      "a": "A question matches pre-generated curated answers first; then it searches the published articles, notes, and answers; anything still unmatched goes to a live service that answers from retrieved public content, single-turn and source-cited.",
      "full": "**Asking works without a model.** The common questions have pre-generated curated answers that appear as soon as they match; anything else runs a full-text search across the published articles, notes, and answers.\n\nIf nothing matches, the question goes to a live same-origin service: it retrieves this site's public content, hands the retrieved passages to a model for a source-grounded answer, and gates the browser entry point with a challenge and quotas. Answers stay single-turn and cite the pages they came from.\n\nEither way there is no long-term memory and no speaking on the author's behalf; when in doubt, trust the linked public page."
    },
    {
      "url": "/en/answers/ai-practice/",
      "q": "What AI practices does this site document?",
      "a": "Three layers — study notes on transformers and deep learning, source-reading notes on agent mechanics (agent loop, tools, context compression, multi-agent collaboration), and small tools built from them, such as EnCoder and QQbot.",
      "full": "**AI is the main line here, and the writing sits in three layers, from mechanism to something that runs.**\n\nThe first layer is fundamentals: the [transformer notes](/en/2026/04/04/transformer-learning-notes/) walk through tokens, positional encoding, Q/K/V attention, multi-head attention, and layer norm in data-flow order, while Simple_CNN reproduces the path from convolution and pooling to a full training run.\n\nThe second layer is agent engineering: reading three Claude Code implementations side by side ([the notebook](/en/2026/08/23/agent-engineering-from-claude-code/)) lines up the agent loop, tool definitions, context injection and compression, parallel tools and sub-agents, multi-agent collaboration, and security boundaries. Minimind-notes covers model architecture and training methods.\n\nThe third layer is tooling that runs: EnCoder extends a minimal agent with cron scheduling, long-term memory, an agent team, and task management; QQbot uses pi as its brain and NapCatQQ as its connection, covering knowledge Q&A, timetable lookup, group management, long-term memory, and hot model switching. The project list is on the [projects page](/en/projects/)."
    },
    {
      "url": "/en/answers/what-is-this-site/",
      "q": "What is this site?",
      "a": "HYD's personal site, recording the path through AI engineering and LLMs — articles, notes, projects, and a curated FAQ, built with Astro, Starlight, and the Refined-X starter so one corpus serves readers, search engines, and AI agents.",
      "full": "**This is HYD's personal site.** Most of it is a record of learning: notes on AI engineering, LLMs, and agents, alongside the projects that came out of them and shorter pieces written along the way.\n\nIt runs on Astro and Starlight over the Refined-X publishing starter. Articles, notes, answers, and projects are written in Markdown and YAML, and each build produces both the pages people read and the same corpus as Markdown mirrors, llms.txt, and JSON endpoints, so search engines and AI agents can read it directly.\n\nFor the person, see the [about page](/en/about/); for the work, the [projects page](/en/projects/); for direct answers, ask on this site or browse the [FAQ](/en/answers/)."
    },
    {
      "url": "/en/answers/where-articles-were/",
      "q": "Where were the earlier posts published?",
      "a": "On CSDN from the summer of 2025 (blog.csdn.net/2401_87876529) — Python and data analysis first, then transformers, LLMs, and agents. New writing moved here in September 2026; the old posts stay up but are no longer updated.",
      "full": "**From the summer of 2025 until September 2026 the writing lived on CSDN — about twenty posts:** https://blog.csdn.net/2401_87876529\n\nThe first half was fundamentals: Python data structures, NumPy and pandas, then data analysis and visualization, with a few competitions and small projects in between. The second half turned to AI — from transformers through tool calling, the agent loop, multi-agent setups, and Claude Code, plus engineering questions like prompt-injection defences and agent checkpoints.\n\nNew writing happens here now; the CSDN archive stays online but is no longer updated. Moving also meant re-ordering the old notes: [the transformer piece](/en/2026/04/04/transformer-learning-notes/) was rewritten into its current shape after the move, and the move itself is written up in the note [From CSDN to a site of my own](/en/notes/from-csdn/)."
    },
    {
      "url": "/en/answers/open-source-projects/",
      "q": "Which open source projects are here?",
      "a": "Six so far — EnCoder, QQbot, Minimind-notes, Simple_CNN, interview-skill, and homework-web_blog — mostly agent tooling and reproductions of deep-learning basics.",
      "full": "**The public work comes down to two things: agent tooling, and reproductions of deep-learning basics.** Repositories are on GitHub: https://github.com/HYDtomako\n\n**EnCoder** extends CoreCoder — a minimal agent — with cron scheduling, long-term memory, an agent team, and task management. **QQbot** pairs pi as the brain with NapCatQQ as the connection, covering knowledge Q&A, timetable lookup, group management, scheduled tasks, long-term memory, and hot model switching.\n\n**Minimind-notes** works through model architecture and training methods, and **Simple_CNN** reproduces convolution and pooling through a full training run. The other two are practice: **interview-skill** pairs a job description with your resume for targeted interview prep, and **homework-web_blog** is the final project for a Python web course.\n\nStatus, tags, and repository links for each are on the [projects page](/en/projects/)."
    },
    {
      "url": "/en/answers/who-is-author/",
      "q": "Who is the author?",
      "a": "HYD is a Data Science and Big Data Technology student at Qingdao Institute of Technology (class of 2024), focused on AI agents and AI-native products — he likes pushing what he learns into small tools that actually run, then open-sourcing them.",
      "full": "**HYD** studies Data Science and Big Data Technology at Qingdao Institute of Technology (class of 2024) and works on AI agents and AI-native products, moving between code, papers, and small tools.\n\nRather than leaving what he learns in notes, he pushes it to the point where it runs: read the source until it can be restated, turn the idea into a tool, then come back here to write it up. Public projects live on GitHub (https://github.com/HYDtomako), from agent tooling to reproductions of deep-learning basics.\n\nThe rest is on the [about page](/en/about/): anime, music, and landscapes picked up on walks."
    }
  ],
  "items": [
    {
      "type": "article",
      "url": "/en/2026/08/23/agent-engineering-from-claude-code/",
      "title": "Three Claude Code implementations: an agent engineering notebook",
      "excerpt": "Agent engineering notes drawn from three implementations. CoreCoder is a minimal implementation written by hand in Python, Claude Code is the production implementation, and learn-claude-code is the teaching implementation. Coverage spans the Agent Loop's transition condition and interrupt repair, tool definitions and file-editing strategy, context injection and three tiers of compression, the long-lived state of QueryEngine, parallel tools and sub-agents, the Hook and Task extension points, multi-agent collaboration, memory / MCP / background tasks / scheduled tasks, and the security defenses around paths and commands.",
      "tags": [
        "Agent",
        "Claude Code",
        "source reading",
        "engineering practice"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-08-23"
    },
    {
      "type": "article",
      "url": "/en/2026/04/04/transformer-learning-notes/",
      "title": "Transformer learning notes: from the overall architecture to multi-head attention",
      "excerpt": "Transformer study notes ordered whole-first and then part-by-part: the data flow through the encoder and the decoder; the three questions to answer before learning large models (neural networks, attention, what PyTorch is made of); what Token, the word embedding matrix, and positional encoding each solve; the meaning of Q, K, and V, why the Q·K dot product stands for relevance, and why the dot product is divided by the square root of the dimension before softmax; the difference between self-attention and cross-attention, and why cross-attention needs no mask; training predicts several tokens in parallel while inference generates one token at a time, which is why a causal mask is needed to prevent peeking, implemented by setting later positions to negative infinity so that softmax turns them into 0; the definitions of the feed-forward network, multi-head attention, and layer normalization, including how layer norm and batch norm differ in which dimension they normalize over.",
      "tags": [
        "Transformer",
        "Deep learning",
        "Attention mechanism",
        "Study notes"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-04-04"
    },
    {
      "type": "note",
      "url": "/en/notes/from-csdn/",
      "title": "From CSDN to a site of my own",
      "excerpt": "A summary of the CSDN period — Python, NumPy/pandas, data analysis, visualization, and a few competition projects first; then transformers, LLMs, and agents (tool calling, the agent loop, multi-agent setups, prompt / context / harness, Claude Code, prompt-injection defences, agent checkpoints). From September 2026 the blog lives on my own site; the old CSDN posts stay up but are no longer updated.",
      "tags": [
        "notes",
        "writing"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-09-24"
    },
    {
      "type": "note",
      "url": "/en/notes/interview-questions/",
      "title": "Two or three small-company interviews: eight questions on agents and LLMs",
      "excerpt": "A debrief of two or three interviews at small companies. The projects were one agent and one LLM, and the questions landed in the same two places — why GQA works (MHA's dimensional expressiveness, MQA's KV cache, GQA as the middle ground), three layers of prompt-injection defence (model / agent / permissions), VRAM and CPU-and-memory contention with a hundred-plus concurrent users, what to do when a sub-agent gets stuck (timeouts and a scheduler), which fields a trace should observe and the ten questions it must answer, recovering information lost in summary compression, what a high-risk approval prompt has to show, and saving checkpoints by event rather than per step.",
      "tags": [
        "notes",
        "interviews",
        "Agent",
        "LLM"
      ],
      "series": "",
      "seriesName": "",
      "date": "2026-08-21"
    },
    {
      "type": "answer",
      "title": "How can AI agents read this site?",
      "excerpt": "The build generates llms.txt and llms-full.txt indexes, a Markdown mirror per page, JSON endpoints for articles, profile, and search, plus an OpenAPI description — so agents can cite material without parsing page layouts.",
      "url": "/en/answers/agent-ready/"
    },
    {
      "type": "answer",
      "title": "How can I collaborate with HYD?",
      "excerpt": "Email HYDhyd0505@gmail.com, or open an issue or a pull request as HYDtomako on GitHub — AI agent practice, open-source collaboration, and publishing setups are all welcome.",
      "url": "/en/answers/collaborate/"
    },
    {
      "type": "answer",
      "title": "How do search and asking work here?",
      "excerpt": "A question matches pre-generated curated answers first; then it searches the published articles, notes, and answers; anything still unmatched goes to a live service that answers from retrieved public content, single-turn and source-cited.",
      "url": "/en/answers/live-ask/"
    },
    {
      "type": "answer",
      "title": "What AI practices does this site document?",
      "excerpt": "Three layers — study notes on transformers and deep learning, source-reading notes on agent mechanics (agent loop, tools, context compression, multi-agent collaboration), and small tools built from them, such as EnCoder and QQbot.",
      "url": "/en/answers/ai-practice/"
    },
    {
      "type": "answer",
      "title": "What is this site?",
      "excerpt": "HYD's personal site, recording the path through AI engineering and LLMs — articles, notes, projects, and a curated FAQ, built with Astro, Starlight, and the Refined-X starter so one corpus serves readers, search engines, and AI agents.",
      "url": "/en/answers/what-is-this-site/"
    },
    {
      "type": "answer",
      "title": "Where were the earlier posts published?",
      "excerpt": "On CSDN from the summer of 2025 (blog.csdn.net/2401_87876529) — Python and data analysis first, then transformers, LLMs, and agents. New writing moved here in September 2026; the old posts stay up but are no longer updated.",
      "url": "/en/answers/where-articles-were/"
    },
    {
      "type": "answer",
      "title": "Which open source projects are here?",
      "excerpt": "Six so far — EnCoder, QQbot, Minimind-notes, Simple_CNN, interview-skill, and homework-web_blog — mostly agent tooling and reproductions of deep-learning basics.",
      "url": "/en/answers/open-source-projects/"
    },
    {
      "type": "answer",
      "title": "Who is the author?",
      "excerpt": "HYD is a Data Science and Big Data Technology student at Qingdao Institute of Technology (class of 2024), focused on AI agents and AI-native products — he likes pushing what he learns into small tools that actually run, then open-sourcing them.",
      "url": "/en/answers/who-is-author/"
    }
  ]
}