--- id: "/new/2026-w42/page/3/" title: "Index additions: 2026-W42 · page 3" creator: null creator_url: null creator_x: null url: "https://skillissue.dev/new/2026-w42/page/3/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null access: null models: null source_date: null date_added: null --- # Index additions: 2026-W42 Resources added to the index in this ISO week. This is a website archive, not a sent newsletter. [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 141 resources · page 3 of 5 ## Prompting - ### [Prompting best practices (Claude docs)](/prompting/model-specific-guides/anthropic-claude-prompting-best-practices/index.md) by [Anthropic](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) Current-model guidance in one page: XML structure, examples, thinking, agentic use. (Old use-xml-tags, multishot and extended-thinking-tips URLs redirect here.) Intermediate · West · closed resource · en - ### [Prompting Fundamentals and How to Apply them Effectively](/prompting/prompting-fundamentals/eugeneyan-prompting-fundamentals/index.md) by [Eugene Yan](https://eugeneyan.com/writing/prompting/) [@eugeneyan](https://twitter.com/eugeneyan) Practitioner write-up applying core techniques to real tasks. Intermediate · West · closed resource · en - ### [Structured outputs (Gemini API)](/prompting/reasoning-and-structured-output/google-gemini-structured-output/index.md) by [Google](https://ai.google.dev/gemini-api/docs/structured-output) Gemini's equivalent: constrain responses to a JSON schema. Intermediate · West · open resource · en - ### [Prompt engineering how-to (Llama docs)](/prompting/model-specific-guides/meta-llama-prompting-guide/index.md) by [Meta](https://dev.meta.ai/llama/docs/how-to-guides/prompting) Official guide for prompting open-weight Llama models. Intermediate · West · closed resource · en - ### [GPT-5 prompting guide](/prompting/model-specific-guides/openai-gpt-5-prompting-guide/index.md) by [OpenAI](https://developers.openai.com/cookbook/examples/gpt-5/gpt-5_prompting_guide) Model-specific advice on agentic eagerness, tool preambles and instruction conflicts. Intermediate stale · West · closed resource · en - ### [Reasoning best practices](/prompting/reasoning-and-structured-output/openai-reasoning-best-practices/index.md) by [OpenAI](https://developers.openai.com/api/docs/guides/reasoning-best-practices) When to pick a reasoning model and how prompting them differs from chat models. Intermediate · West · closed resource · en - ### [Structured model outputs](/prompting/reasoning-and-structured-output/openai-structured-outputs/index.md) by [OpenAI](https://developers.openai.com/api/docs/guides/structured-outputs) How to get schema-valid JSON instead of hoping the model formats it right. Intermediate · West · closed resource · en - ### [grok-prompts (published system prompts)](/prompting/system-prompts/xai-grok-prompts/index.md) by [xAI](https://github.com/xai-org/grok-prompts) Inspect system prompts published by their original provider. Intermediate · West · open resource · en - ### [Prompt Engineering](/prompting/prompting-fundamentals/lilianweng-prompt-engineering/index.md) by [Lilian Weng](https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/) [@lilianweng](https://twitter.com/lilianweng/) Dense, research-backed survey of prompting methods with citations. Advanced · West · closed resource · en - ### [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](/prompting/prompting-fundamentals/schulhoff-the-prompt-report/index.md) by [Sander Schulhoff et al.](https://arxiv.org/abs/2406.06608) A broad research taxonomy for comparing prompting techniques and finding their sources. Advanced · West · open resource · en - ### [DSPy](/prompting/prompt-optimization/stanford-dspy/index.md) by [Stanford NLP](https://dspy.ai/current/) Build modular model programs and improve them against a metric. Advanced · West · open resource · en - ### [Self-Consistency Improves Chain of Thought Reasoning in Language Models](/prompting/reasoning-and-structured-output/wang-self-consistency/index.md) by [Xuezhi Wang et al.](https://arxiv.org/abs/2203.11171) Sample several reasoning paths and take the majority answer. Advanced · West · open resource · en - ### [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](/prompting/reasoning-and-structured-output/wei-chain-of-thought-prompting/index.md) by [Jason Wei et al.](https://arxiv.org/abs/2201.11903) Early research on using worked reasoning examples to improve performance on reasoning tasks. Advanced · West · open resource · en - ### [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](/prompting/reasoning-and-structured-output/yao-tree-of-thoughts/index.md) by [Shunyu Yao et al.](https://arxiv.org/abs/2305.10601) Search over branching reasoning steps; basis for many planning approaches. Advanced · West · open resource · en ## Evaluation - ### [AI Evals FAQ](/evaluation/application-evals/hamel-husain-ai-evals-faq/index.md) by [Hamel Husain and Shreya Shankar](https://hamel.dev/blog/posts/evals-faq/) Practical answers about error analysis, annotation and reliable evaluators. Intermediate · West · closed resource · en - ### [Your AI Product Needs Evals](/evaluation/application-evals/hamel-husain-your-ai-product-needs-evals/index.md) by [Hamel Husain](https://hamel.dev/blog/posts/evals/) Build a feedback loop from real failures, not general benchmark scores. Intermediate · West · closed resource · en - ### [SWE-bench Leaderboards](/evaluation/agent-evals/swe-bench-team-swe-bench-leaderboards/index.md) by [SWE-bench team (Princeton/Stanford)](https://www.swebench.com/) Understand coding-agent scores in terms of resolved repository tasks. Intermediate · West · closed resource · en - ### [lm-evaluation-harness](/evaluation/eval-harnesses/eleutherai-lm-evaluation-harness/index.md) by [EleutherAI](https://github.com/EleutherAI/lm-evaluation-harness) Run model benchmarks through reusable task and backend interfaces. Advanced · West · open resource · en - ### [Evaluating the Effectiveness of LLM-Evaluators (LLM-as-Judge)](/evaluation/llm-as-judge/eugene-yan-evaluating-the-effectiveness-of-llm-evaluators/index.md) by [Eugene Yan](https://eugeneyan.com/writing/llm-evaluators/) [@eugeneyan](https://twitter.com/eugeneyan) Compare model-based graders against the judgments they must approximate. Advanced · West · closed resource · en - ### [simple-evals](/evaluation/eval-harnesses/openai-simple-evals/index.md) by [OpenAI](https://github.com/openai/simple-evals) Read reference evaluation code with an explicit maintenance caveat. Advanced stale · West · open resource · en - ### [Inspect](/evaluation/eval-harnesses/uk-ai-security-institute-inspect/index.md) by [UK AI Security Institute and Meridian Labs](https://inspect.aisi.org.uk/) Compose evaluation datasets, agents, tools and scorers. Advanced · West · closed resource · en ## Foundations - ### [The Illustrated Transformer](/foundations/llm-fundamentals/jay-alammar-the-illustrated-transformer/index.md) by [Jay Alammar](https://jalammar.github.io/illustrated-transformer/) See how attention and encoder-decoder blocks fit together. Beginner · West · closed resource · en - ### [Neural Networks: Zero to Hero](/foundations/courses-and-learning-paths/andrej-karpathy-neural-networks-zero-to-hero/index.md) by [Andrej Karpathy](https://karpathy.ai/zero-to-hero.html) [@karpathy](https://twitter.com/karpathy) Learn neural networks by implementing them in Python. Intermediate · West · closed resource · en - ### [Hugging Face LLM Course](/foundations/courses-and-learning-paths/hugging-face-hugging-face-llm-course/index.md) by [Hugging Face](https://huggingface.co/learn/llm-course) A structured route through the Hugging Face ecosystem. Intermediate · other · open resource · en - ### [LLMs-from-scratch (book code)](/foundations/from-scratch-implementations/sebastian-raschka-llms-from-scratch/index.md) by [Sebastian Raschka](https://github.com/rasbt/LLMs-from-scratch) Follow a GPT implementation rather than treating the model as a black box. Intermediate · West · closed resource · en - ### [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) by [Yan, Bischof, Frye, Husain, Liu, Shankar](https://applied-llms.org/) Cross-functional lessons from building language-model applications. Intermediate · West · closed resource · en - ### [Lil'Log](/foundations/practitioner-overviews/lilian-weng-lil-log/index.md) by [Lilian Weng](https://lilianweng.github.io/) [@lilianweng](https://twitter.com/lilianweng/) Research learning notes that connect methods to their literature. Advanced · West · closed resource · en ## Model Training - ### [Qwen2.5 LoRA fine-tuning walkthrough (Chinese)](/model-training/fine-tuning/datawhale-qwen25-lora/index.md) by [Datawhale self-llm contributors](https://github.com/datawhalechina/self-llm) Follow a concrete Chinese LoRA recipe from instruction records to a trained adapter and inference. Intermediate · CN · open resource · zh - ### [ruGPT training and fine-tuning examples](/model-training/fine-tuning/ai-forever-rugpt-training/index.md) by [SberDevices / ai-forever](https://github.com/ai-forever/ru-gpts) Inspect Russian-model fine-tuning and pretraining scripts, with explicit warnings about the legacy environment. Advanced · RU · open resource · en - ### [GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture](/model-training/pretraining/gigachat-family-moe-training-report/index.md) by [GigaChat team / SaluteDevices](https://arxiv.org/abs/2506.09440v1) Study a Russian-origin model team’s account of mixture-of-experts architecture, pretraining and evaluation. Advanced · RU · open resource · en - ### [LlamaFactory](/model-training/fine-tuning/hiyouga-llamafactory/index.md) by [hiyouga (Yaowei Zheng) et al.](https://github.com/hiyouga/LlamaFactory) Compare adaptation methods within a shared training interface. Advanced · CN · open resource · en - ### [TRL - Transformers Reinforcement Learning](/model-training/post-training-rl/hugging-face-trl-transformers-reinforcement-learning/index.md) by [Hugging Face](https://huggingface.co/docs/trl/index) Find training interfaces for supervised and preference-based adaptation. Advanced · other · closed resource · en [Previous page](/new/2026-w42/page/2/index.md) [Next page](/new/2026-w42/page/4/index.md) [Plain-text Markdown copy](/new/2026-w42/page/3/index.md)