Tag
A tweet noting that an LLM-focused engineering resource still remains a great starting point for projects, though it may need an update for 2027.
A practitioner's listicle outlining 15+ essential portfolio projects for aspiring Agentic AI Engineers, covering async orchestration, strict tool routing, memory eviction, self-healing ReAct loops, human-in-the-loop gates, trajectory evaluation CI, agent observability, prompt-injection defenses, sandboxed execution, and cost kill-switches.
推文推荐斯坦福 CS329Z《工程化 AI 智能体》课程，并附上首讲详细笔记，涵盖智能体循环、Actor 模型到 ReAct 的发展史、harness 的关键作用，以及构建、评估与调试 AI 智能体的核心理念。
A developer discusses how Anthropic's backend rewrite to Rust involved building robust evals and parallel-running systems to verify correctness, arguing that constraining non-deterministic AI tools is the key challenge in AI-assisted coding right now.
LangChain shared a recap of Harrison Chase's conversation with Harry Stebbings on The Twenty Minute VC, highlighting that an agent = model + context + harness, and that improving any of the three can boost agent performance.
A practitioner weighs three designs for adding persistent knowledge-base spreadsheets to a chat agent's existing tools, leaning toward a dedicated analyze_knowledge_spreadsheet tool with clear routing descriptions and a routing test, while asking the community for missed approaches.
斯坦福大学免费提供CME 295课程，涵盖从Transformer基础到LLM训练与应用的完整知识体系，适合生成式AI和智能体AI的学习者。
This article discusses how retries in AI systems, particularly with LLMs and agents, can exacerbate failures when underlying issues are not addressed, leading to repeated mistakes with increased cost and latency.
The author introduces the conceptual evolution from prompt engineering to graph engineering, pointing out that graph engineering essentially uses directed graphs (including cycles) and finite state machines (FSM) to manage the collaborative execution of multiple agents, which is a natural development in the current engineering phase.
Explains the difference between traditional RAG and Agentic RAG, highlighting that Agentic RAG adds a decision layer for iterative retrieval and multi-source reasoning, and mentions an upcoming bootcamp.
This article by yan5xu (former ManusAI) proposes a spiral evolution model for LLM engineering paradigms: from Prompt Engineering (2022-2024) to Context Engineering (2025), then to Harness Engineering (2026-), and discusses the bottlenecks and driving factors at each stage.
A page from Modal's LLM Engineer's Almanac that provides an interactive explorer for understanding low-precision floating-point formats like bf16 and fp4.
A free, open-source 8-week hands-on LLM engineering course by Ed Donner, featuring weekly projects and covering topics like Ollama, Llama 3.2, and AI coding tools.
The article discusses Andrej Karpathy's advice on leveraging LLMs despite their cognitive deficits, highlighting a case study where custom configuration (CLAUDE.md) significantly reduced error rates.
This article outlines a 2026 roadmap for LLM engineering, detailing eight key pillars including prompt engineering, RAG systems, and context management, while providing curated free and open-source resources for each.
Maxime Labonne's open-source LLM Course repo organizes free learning resources into LLM Fundamentals, LLM Scientist, and LLM Engineer tracks, with curated Colab notebooks for fine-tuning, merging, quantizing, and evaluating large language models.
A project-based roadmap for learning LLM engineering by building key components from tokenizers to serving stacks, including hardware foundations and post-training techniques.
Anthropic publishes engineering guidelines for building effective AI agents, advocating for simple, composable patterns and direct API usage over complex frameworks. The article distinguishes between workflows and autonomous agents, providing practical advice on when to use each architecture.