--- id: "/search/" title: "Search and filter resources" creator: null creator_url: null url: "https://skillissue.dev/search/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null models: null source_date: null date_added: null --- # Search the index Search titles, creators and short descriptions. Filters combine. Nothing you type is sent or saved. JavaScript is off: all resources are listed below. Use your browser’s Find, or the [topic index](/index.md) and [level pages](/start-here/index.md). 133 resources No matching resources. Clear a filter or reset your search. - [AGENTS.md](/context-engineering/agent-instruction-files/agentsmd-agents-md/index.md) · AGENTS.md (multi-vendor open format) Open format for a repo instruction file that coding agents read. - [Interactive prompt engineering tutorial](/prompting/prompting-fundamentals/anthropic-prompt-eng-interactive-tutorial/index.md) · Anthropic Hands-on notebook course: you edit prompts and see results, no coding needed. - [Prompt engineering overview (Claude docs)](/prompting/prompting-fundamentals/anthropic-prompt-engineering-overview/index.md) · Anthropic Official starting point for prompting Claude; points to the best-practices reference and the interactive tutorials. - [Prompt Engineering Guide](/prompting/prompting-fundamentals/dair-prompt-engineering-guide/index.md) · DAIR.AI Broad, frequently updated reference of named prompting techniques. - [Prompt design strategies (Gemini API)](/prompting/model-specific-guides/google-gemini-prompt-design-strategies/index.md) · Google Google's official prompting guide with clear before/after examples. - [The Illustrated Transformer](/foundations/llm-fundamentals/jay-alammar-the-illustrated-transformer/index.md) · Jay Alammar See how attention and encoder-decoder blocks fit together. - [Instruction prompting (Learn Prompting)](/prompting/prompting-fundamentals/learnprompting-learn-prompting/index.md) · Sander Schulhoff / Learn Prompting Practice clear task instructions with a free-to-read lesson, then test where an instruction stops working. - [A practical guide to building agents (PDF)](/agents/agent-design-patterns/openai-practical-guide-to-building-agents/index.md) · OpenAI Plain-language foundations: when to build an agent, orchestration, guardrails. - [Prompt engineering (OpenAI API docs)](/prompting/prompting-fundamentals/openai-prompt-engineering-guide/index.md) · OpenAI OpenAI's official baseline on message roles, instructions and examples. - [GigaChat prompt engineering fundamentals](/prompting/model-specific-guides/sber-gigachat-prompt-engineering/index.md) · Sber / GigaChat A Russian-language checklist for making GigaChat requests specific, testable and easier to revise. - [Andrej Karpathy on X](/top-x-creators/practitioners/x-andrej-karpathy/index.md) · Andrej Karpathy AI explanations and practical model-use observations from a neural-network educator. - [GigaChain agent cookbook](/agents/tool-use-and-mcp/ai-forever-gigachain-cookbook/index.md) · GigaChain / ai-forever Russian notebooks connect GigaChat to typed functions, retrieval and MCP tools. - [GigaChat Python SDK](/lab-practices/other-labs/ai-forever-gigachat-sdk/index.md) · GigaChain / AI Forever An SDK reference for calling the GigaChat service from Python. - [Neural Networks: Zero to Hero](/foundations/courses-and-learning-paths/andrej-karpathy-neural-networks-zero-to-hero/index.md) · Andrej Karpathy Learn neural networks by implementing them in Python. - [Equipping agents for the real world with Agent Skills](/context-engineering/agent-instruction-files/anthropic-agent-skills/index.md) · Anthropic Packaging instructions and scripts as loadable skills. - [Anthropic Engineering blog](/lab-practices/anthropic/anthropic-anthropic-engineering-blog/index.md) · Anthropic Find first-party accounts of engineering decisions behind Claude systems. - [Building Effective AI Agents](/agents/agent-design-patterns/anthropic-building-effective-agents/index.md) · Anthropic Workflows vs agents and the core patterns; argues to start simple. Readable without code. - [Best practices for Claude Code](/agents/coding-agents/anthropic-claude-code-best-practices/index.md) · Anthropic Concrete coding-agent workflow habits: plan, verify, manage context. - [Claude Cookbooks](/lab-practices/anthropic/anthropic-claude-cookbooks/index.md) · Anthropic Code recipes for integrating Claude capabilities into applications. - [Prompting best practices (Claude docs)](/prompting/model-specific-guides/anthropic-claude-prompting-best-practices/index.md) · Anthropic Current-model guidance in one page: XML structure, examples, thinking, agentic use. (Old use-xml-tags, multishot and extended-thinking-tips URLs redirect here.) - [Effective context engineering for AI agents](/context-engineering/context-management/anthropic-effective-context-engineering/index.md) · Anthropic Treats context as a finite budget: compaction, notes, sub-agents. - [Responsible Scaling Policy](/frontier/policy-and-governance/anthropic-responsible-scaling/index.md) · Anthropic Read a lab’s published risk-governance commitments and revision history. - [Artificial Analysis](/frontier/model-releases/artificial-analysis-artificial-analysis/index.md) · Artificial Analysis Compare model and provider characteristics in one public analysis hub. - [Hello-Agents: build agents in Chinese](/agents/agent-design-patterns/datawhale-hello-agents/index.md) · Sizhou Chen, Tao Sun, Shufan Jiang and Datawhale contributors Chinese explanations and code move from model calls to ReAct, planning and reflection. - [Qwen2.5 LoRA fine-tuning walkthrough (Chinese)](/model-training/fine-tuning/datawhale-qwen25-lora/index.md) · Datawhale self-llm contributors Follow a concrete Chinese LoRA recipe from instruction records to a trained adapter and inference. - [DeepSeek API Docs](/lab-practices/chinese-labs/deepseek-deepseek-api-docs/index.md) · DeepSeek Start a DeepSeek API integration from the provider's own documentation. - [DeepSeek on GitHub (model repos, tech reports, open-infra-index)](/lab-practices/chinese-labs/deepseek-deepseek-on-github/index.md) · DeepSeek A first-party directory of DeepSeek repositories. - [Epoch AI - Data on the trajectory of AI](/frontier/trends-and-forecasts/epoch-ai-epoch-ai-data-on-the-trajectory-of-ai/index.md) · Epoch AI Explore longitudinal datasets about models, compute and infrastructure. - [Prompting Fundamentals and How to Apply them Effectively](/prompting/prompting-fundamentals/eugeneyan-prompting-fundamentals/index.md) · Eugene Yan Practitioner write-up applying core techniques to real tasks. - [Google DeepMind Research](/lab-practices/google-deepmind/google-deepmind-google-deepmind-research/index.md) · Google DeepMind Locate DeepMind research and the projects behind it. - [Gemini API cookbook](/lab-practices/google-deepmind/google-gemini-api-cookbook/index.md) · Google Explore Gemini features through official notebooks and examples. - [Structured outputs (Gemini API)](/prompting/reasoning-and-structured-output/google-gemini-structured-output/index.md) · Google Gemini's equivalent: constrain responses to a JSON schema. - [AI Evals FAQ](/evaluation/application-evals/hamel-husain-ai-evals-faq/index.md) · Hamel Husain and Shreya Shankar Practical answers about error analysis, annotation and reliable evaluators. - [Your AI Product Needs Evals](/evaluation/application-evals/hamel-husain-your-ai-product-needs-evals/index.md) · Hamel Husain Build a feedback loop from real failures, not general benchmark scores. - [AI Agents Course](/agents/agent-design-patterns/hf-ai-agents-course/index.md) · Hugging Face Free course from 'what is an agent' to building one. - [Hugging Face Daily Papers](/frontier/research-feeds/hugging-face-hugging-face-daily-papers/index.md) · Hugging Face A community-curated route into newly discussed AI papers. - [Hugging Face LLM Course](/foundations/courses-and-learning-paths/hugging-face-hugging-face-llm-course/index.md) · Hugging Face A structured route through the Hugging Face ecosystem. - [Agents](/agents/agent-design-patterns/huyenchip-agents/index.md) · Chip Huyen Long-form essay on tools, planning, failure modes and evaluating agents. - [Critiquing Anthropic’s Variant of Pacing the Frontier (ChinAI)](/frontier/policy-and-governance/jeffrey-ding-chinai-newsletter/index.md) · Jeffrey Ding A free ChinAI essay examining arguments about international AI competition. - [Letta documentation](/context-engineering/memory/letta-memory-docs/index.md) · Letta Explore documentation for agents that keep state across interactions. - [Model Context Protocol docs](/agents/tool-use-and-mcp/mcp-model-context-protocol-docs/index.md) · MCP project The spec and docs for connecting tools and data to agents. - [Llama Cookbook](/lab-practices/meta/meta-llama-cookbook/index.md) · Meta First-party examples for building applications around Llama. - [Prompt engineering how-to (Llama docs)](/prompting/model-specific-guides/meta-llama-prompting-guide/index.md) · Meta Official guide for prompting open-weight Llama models. - [Mistral AI docs](/lab-practices/other-labs/mistral-ai-mistral-ai-docs/index.md) · Mistral AI Find Mistral's API and model-integration documentation. - [Mistral cookbook](/lab-practices/other-labs/mistral-ai-mistral-cookbook/index.md) · Mistral AI Notebook examples from Mistral and its contributors. - [Kimi API Platform docs](/lab-practices/chinese-labs/moonshot-ai-kimi-api-platform-docs/index.md) · Moonshot AI Follow the official quickstart for the hosted Kimi API. - [State of AI Report 2026](/frontier/annual-reports/nathan-benaich-air-street-capital-state-of-ai-report-2026/index.md) · Nathan Benaich / Air Street Capital A yearly synthesis of AI research, industry and policy developments. - [The current balance of power in open models (Interconnects)](/frontier/trends-and-forecasts/nathan-lambert-interconnects/index.md) · Nathan Lambert A free Interconnects essay distinguishing open-weight and closed-model ecosystems. - [NIST AI Risk Management Framework](/security-and-red-teaming/threat-frameworks-and-standards/nist-nist-ai-risk-management-framework/index.md) · NIST A government reference for organizing AI risk-management work. - [OpenAI Agents SDK](/agents/harnesses-and-frameworks/openai-agents-sdk/index.md) · OpenAI Lightweight framework: handoffs, guardrails, tracing. - [GPT-5 prompting guide](/prompting/model-specific-guides/openai-gpt-5-prompting-guide/index.md) · OpenAI Model-specific advice on agentic eagerness, tool preambles and instruction conflicts. - [OpenAI Cookbook](/lab-practices/openai/openai-openai-cookbook/index.md) · OpenAI Browse worked examples for OpenAI APIs and applications. - [Reasoning best practices](/prompting/reasoning-and-structured-output/openai-reasoning-best-practices/index.md) · OpenAI When to pick a reasoning model and how prompting them differs from chat models. - [Structured model outputs](/prompting/reasoning-and-structured-output/openai-structured-outputs/index.md) · OpenAI How to get schema-valid JSON instead of hoping the model formats it right. - [OWASP Top 10 for LLM Applications 2025](/security-and-red-teaming/threat-frameworks-and-standards/owasp-gen-ai-security-project-owasp-top-10-for-llm-applications-2025/index.md) · OWASP Gen AI Security Project Use a shared vocabulary for discussing risks in LLM applications. - [Qwen blog](/lab-practices/chinese-labs/qwen-team-alibaba-qwen-blog/index.md) · Qwen team, Alibaba Follow Qwen's own release notes and technical introductions. - [Qwen documentation](/lab-practices/chinese-labs/qwen-team-alibaba-qwen-documentation/index.md) · Qwen team, Alibaba Navigate Qwen deployment, inference and adaptation guidance. - [Qwen3 repo](/lab-practices/chinese-labs/qwen-team-alibaba-qwen3-repo/index.md) · Qwen team, Alibaba Find Qwen3 checkpoints and model-specific usage guidance. - [Context Engineering for Agents](/context-engineering/context-management/rlancemartin-context-engineering-for-agents/index.md) · Lance Martin Write/select/compress/isolate taxonomy of context strategies. - [GigaChat API documentation](/lab-practices/other-labs/sber-gigachat-api/index.md) · Sber A Russian-language first-party guide to integrating GigaChat. - [LLMs-from-scratch (book code)](/foundations/from-scratch-implementations/sebastian-raschka-llms-from-scratch/index.md) · Sebastian Raschka Follow a GPT implementation rather than treating the model as a black box. - [Simon Willison on prompt injection](/security-and-red-teaming/prompt-injection/simon-willison-simon-willison-on-prompt-injection/index.md) · Simon Willison Follow an ongoing public record of prompt-injection research. - [Simon Willison's Weblog](/frontier/research-feeds/simon-willison-simon-willison-s-weblog/index.md) · Simon Willison Follow hands-on notes and commentary on model releases and tools. - [A local build is not a release](/build-logs/originals/skillissue-static-build-gate/index.md) · skill issue Our original build account separates generated-page checks from browser testing and release authorization. - [AI Index (Stanford HAI)](/frontier/annual-reports/stanford-hai-ai-index/index.md) · Stanford HAI Compare AI developments through a broad annual statistical report. - [SWE-bench Leaderboards](/evaluation/agent-evals/swe-bench-team-swe-bench-leaderboards/index.md) · SWE-bench team (Princeton/Stanford) Understand coding-agent scores in terms of resolved repository tasks. - [The lethal trifecta for AI agents](/security-and-red-teaming/agent-and-tool-security/willison-lethal-trifecta/index.md) · Simon Willison A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs. - [Building search-based RAG with Datasette](/build-logs/external-builds/willison-search-rag-build/index.md) · Simon Willison A real prototype log follows full-text retrieval through implementation, model changes and missing evals. - [Chip Huyen on X](/top-x-creators/practitioners/x-chip-huyen/index.md) · Chip Huyen AI system-design notes that connect model behavior, tools and production choices. - [Eugene Yan on X](/top-x-creators/practitioners/x-eugene-yan/index.md) · Eugene Yan Applied AI systems and evaluation lessons from a practitioner’s public technical writing. - [Simon Willison on X](/top-x-creators/practitioners/x-simon-willison/index.md) · Simon Willison Practical LLM experiments and software-building notes, with links back to detailed write-ups. - [grok-prompts (published system prompts)](/prompting/system-prompts/xai-grok-prompts/index.md) · xAI Inspect system prompts published by their original provider. - [xAI / Grok API docs](/lab-practices/xai/xai-xai-grok-api-docs/index.md) · xAI The official entry point for Grok API capabilities and integration guides. - [Applied LLMs: What We've Learned From A Year of Building with LLMs](/foundations/practitioner-overviews/yan-bischof-frye-husain-liu-shankar-applied-llms-what-we-ve-learned-from-a-year-of-building-with-llms/index.md) · Yan, Bischof, Frye, Husain, Liu, Shankar Cross-functional lessons from building language-model applications. - [Yandex AI Studio SDK](/lab-practices/other-labs/yandex-ai-studio-sdk/index.md) · Yandex Cloud Use the official Python client to understand YandexGPT integrations. - [Z.ai developer docs](/lab-practices/chinese-labs/zhipu-z-ai-z-ai-developer-docs/index.md) · Zhipu / Z.ai An official starting point for accessing Z.ai's GLM service. - [ruGPT training and fine-tuning examples](/model-training/fine-tuning/ai-forever-rugpt-training/index.md) · SberDevices / ai-forever Inspect Russian-model fine-tuning and pretraining scripts, with explicit warnings about the legacy environment. - [Agentic misalignment](/security-and-red-teaming/safety-and-alignment-evals/anthropic-agentic-misalignment/index.md) · Anthropic A controlled study of risky behavior under conflicting agent incentives. - [Effective harnesses for long-running agents](/context-engineering/loop-engineering/anthropic-effective-harnesses-long-running-agents/index.md) · Anthropic Harness design for agents that work across many context windows. - [How we built our multi-agent research system](/agents/multi-agent-systems/anthropic-multi-agent-research-system/index.md) · Anthropic Real production lessons on orchestrator/sub-agent design and its costs. - [Writing effective tools for AI agents](/agents/tool-use-and-mcp/anthropic-writing-tools-for-agents/index.md) · Anthropic How to design, evaluate and improve the tools an agent calls. - [Browser Use](/agents/computer-and-browser-use/browser-use-browser-use/index.md) · Browser Use contributors Inspect a Python library for model-driven browser interaction. - [Context Rot: How Increasing Input Tokens Impacts LLM Performance](/context-engineering/context-management/chroma-context-rot/index.md) · Chroma Measures how output quality drops as input length grows. - [Don't Build Multi-Agents](/agents/multi-agent-systems/cognition-dont-build-multi-agents/index.md) · Cognition The counter-argument: context sharing beats splitting work across agents. - [lm-evaluation-harness](/evaluation/eval-harnesses/eleutherai-lm-evaluation-harness/index.md) · EleutherAI Run model benchmarks through reusable task and backend interfaces. - [Evaluating the Effectiveness of LLM-Evaluators (LLM-as-Judge)](/evaluation/llm-as-judge/eugene-yan-evaluating-the-effectiveness-of-llm-evaluators/index.md) · Eugene Yan Compare model-based graders against the judgments they must approximate. - [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](/security-and-red-teaming/prompt-injection/greshake-indirect-prompt-injection/index.md) · Kai Greshake et al. Foundational public research on indirect prompt injection. Linked only; no payloads reproduced. - [LlamaFactory](/model-training/fine-tuning/hiyouga-llamafactory/index.md) · hiyouga (Yaowei Zheng) et al. Compare adaptation methods within a shared training interface. - [TRL - Transformers Reinforcement Learning](/model-training/post-training-rl/hugging-face-trl-transformers-reinforcement-learning/index.md) · Hugging Face Find training interfaces for supervised and preference-based adaptation. - [12-Factor Agents](/agents/agent-design-patterns/humanlayer-12-factor-agents/index.md) · HumanLayer (Dex Horthy) Principles for agents that hold up in production. - [Embrace The Red](/security-and-red-teaming/prompt-injection/johann-rehberger-embrace-the-red/index.md) · Johann Rehberger Public case reports about security failures in deployed AI products. - [EXAONE 4.0](/lab-practices/other-labs/lg-exaone-4/index.md) · LG AI Research Official model guidance with reasoning and deployment examples. - [Lil'Log](/foundations/practitioner-overviews/lilian-weng-lil-log/index.md) · Lilian Weng Research learning notes that connect methods to their literature. - [LLM Powered Autonomous Agents](/agents/agent-design-patterns/lilianweng-llm-powered-autonomous-agents/index.md) · Lilian Weng Classic overview of planning, memory and tool use in agents. - [Prompt Engineering](/prompting/prompting-fundamentals/lilianweng-prompt-engineering/index.md) · Lilian Weng Dense, research-backed survey of prompting methods with citations. - [LLAMATOR: authorized conversational AI security testing](/security-and-red-teaming/security-tooling/llamator-authorized-testing/index.md) · Roman Neronov, Timur Nizamov and Nikita Ivanov / LLAMATOR A Russian-origin framework for assessing your own chatbots, with reviewable test histories and reports. - [Building syntaqlite with coding agents](/build-logs/external-builds/maganti-syntaqlite-build/index.md) · Lalit Maganti A builder documents a failed agent-led design, a rewrite and the verification work behind a real developer tool. - [Context Engineering for AI Agents: Lessons from Building Manus](/context-engineering/context-management/manus-context-engineering-lessons/index.md) · Manus KV-cache-aware design, file system as memory, keep errors in context. - [MCP reference servers](/agents/tool-use-and-mcp/mcp-reference-servers/index.md) · MCP project Reference implementations to learn MCP server design from. - [A Survey of Context Engineering for LLMs (arXiv 2507.13334)](/context-engineering/context-management/mei-et-al-a-survey-of-context-engineering-for-llms/index.md) · Mei et al. (Chinese Academy of Sciences et al.) A research map of retrieval, context processing and memory systems. - [METR](/frontier/trends-and-forecasts/metr-metr/index.md) · METR Follow research on the capabilities and risks of increasingly autonomous systems. - [MiniMax-M2 repo](/lab-practices/chinese-labs/minimax-minimax-m2-repo/index.md) · MiniMax Examine MiniMax-M2's model release and agent-oriented evaluation report. - [MITRE ATLAS](/security-and-red-teaming/threat-frameworks-and-standards/mitre-mitre-atlas/index.md) · MITRE Connect AI threats with documented techniques, mitigations and cases. - [Kimi K2 repo](/lab-practices/chinese-labs/moonshot-ai-kimi-k2-repo/index.md) · Moonshot AI Read the Kimi K2 model overview and deployment material. - [Reinforcement Learning from Human Feedback (book)](/model-training/post-training-rl/nathan-lambert-reinforcement-learning-from-human-feedback/index.md) · Nathan Lambert A conceptual path through reward modeling and post-training methods. - [RAG Techniques](/context-engineering/retrieval-and-rag/nirdiamant-rag-techniques/index.md) · Nir Diamant and contributors Compare retrieval designs through code-oriented examples. - [garak - LLM vulnerability scanner](/security-and-red-teaming/security-tooling/nvidia-garak-llm-vulnerability-scanner/index.md) · NVIDIA A public scanner project for understanding classes of model failures. - [simple-evals](/evaluation/eval-harnesses/openai-simple-evals/index.md) · OpenAI Read reference evaluation code with an explicit maintenance caveat. - [OpenHands Agent Canvas](/agents/harnesses-and-frameworks/openhands-agent-canvas/index.md) · OpenHands (All Hands AI) Inspect the OpenHands control center and its supported execution backends. - [OpenHands Software Agent SDK](/agents/harnesses-and-frameworks/openhands-openhands/index.md) · OpenHands Open-source agent SDK behind OpenHands, worth reading as a reference harness. - [promptfoo](/security-and-red-teaming/security-tooling/promptfoo-promptfoo/index.md) · promptfoo Inspect a project combining application evaluation and security testing. - [Qwen-Agent](/agents/harnesses-and-frameworks/qwen-team-alibaba-qwen-agent/index.md) · Qwen team, Alibaba A Qwen-focused framework for tool-using applications. - [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](/prompting/prompting-fundamentals/schulhoff-the-prompt-report/index.md) · Sander Schulhoff et al. A broad research taxonomy for comparing prompting techniques and finding their sources. - [Controlling Reasoning Effort in LLMs (Ahead of AI)](/model-training/post-training-rl/sebastian-raschka-ahead-of-ai/index.md) · Sebastian Raschka A free Ahead of AI article on training controllable reasoning effort. - [DSPy](/prompting/prompt-optimization/stanford-dspy/index.md) · Stanford NLP Build modular model programs and improve them against a metric. - [Inspect](/evaluation/eval-harnesses/uk-ai-security-institute-inspect/index.md) · UK AI Security Institute and Meridian Labs Compose evaluation datasets, agents, tools and scorers. - [Unsloth](/model-training/fine-tuning/unsloth-unsloth/index.md) · Unsloth Study local training and adaptation workflows for supported models. - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](/prompting/reasoning-and-structured-output/wang-self-consistency/index.md) · Xuezhi Wang et al. Sample several reasoning paths and take the majority answer. - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](/prompting/reasoning-and-structured-output/wei-chain-of-thought-prompting/index.md) · Jason Wei et al. Early research on using worked reasoning examples to improve performance on reasoning tasks. - [Design Patterns for Securing LLM Agents against Prompt Injections](/security-and-red-teaming/agent-and-tool-security/willison-prompt-injection-design-patterns/index.md) · Simon Willison Summary of a paper's defensive agent architectures. - [Lilian Weng on X](/top-x-creators/practitioners/x-lilian-weng/index.md) · Lilian Weng Research-oriented learning notes on model training, reasoning and agent harnesses. - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](/agents/coding-agents/yang-swe-agent/index.md) · John Yang et al. Research on how the agent-computer interface influences software-engineering performance. - [ReAct: Synergizing Reasoning and Acting in Language Models](/agents/agent-design-patterns/yao-react/index.md) · Shunyu Yao et al. Research on combining reasoning with environment actions, a useful reference for agent-loop design. - [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](/prompting/reasoning-and-structured-output/yao-tree-of-thoughts/index.md) · Shunyu Yao et al. Search over branching reasoning steps; basis for many planning approaches. - [GLM-4.5 repo](/lab-practices/chinese-labs/zhipu-z-ai-glm-4-5-repo/index.md) · Zhipu / Z.ai Inspect GLM release information and usage examples in the official repository. - [nanochat](/model-training/pretraining/andrej-karpathy-nanochat/index.md) · Andrej Karpathy A compact training harness spanning the model-development lifecycle. - [DeepSeek open-infra-index](/lab-practices/chinese-labs/deepseek-deepseek-open-infra-index/index.md) · DeepSeek A directory of DeepSeek's published infrastructure components. - [DeepSeek-R1: Incentivizing Reasoning via RL (arXiv 2501.12948)](/model-training/post-training-rl/deepseek-deepseek-r1-incentivizing-reasoning-via-rl/index.md) · DeepSeek Study the reported reinforcement-learning recipe behind DeepSeek-R1. - [The Smol Training Playbook](/model-training/pretraining/hugging-face-the-smol-training-playbook/index.md) · Hugging Face (SmolLM team) A training account that includes failed experiments and engineering decisions. - [The Ultra-Scale Playbook](/model-training/training-infrastructure/hugging-face-the-ultra-scale-playbook/index.md) · Hugging Face (nanotron) Understand how parallelism changes memory use and training throughput. - [The FineWeb Datasets](/model-training/training-data/huggingface-fineweb/index.md) · Guilherme Penedo and coauthors, Hugging Face Study how filtering and deduplication affect pretraining data. - [The AI Scientist](/lab-practices/other-labs/sakana-ai-scientist/index.md) · Sakana AI and collaborators Inspect a research pipeline for automated experiments and scientific writeups. - [verl (HybridFlow)](/model-training/post-training-rl/verl-project-verl/index.md) · verl project (originated at ByteDance Seed) Explore how an RL training framework coordinates generation and optimization. [Plain-text Markdown copy](/search/index.md)