Skip to content

Sources & Further Reading

  • Intermediate · Module 01
  • Sources for this module
Note
Sources checked: September 2026

Sources reviewed in September 2026: links checked for availability and extended with references for the current state. As the AI landscape evolves quickly, some details may have changed since then.

Sources

  1. Vaswani, A. et al. (2017). Attention Is All You Need. arXiv:1706.03762. https://arxiv.org/abs/1706.03762

  2. Mikolov, T. et al. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781. https://arxiv.org/abs/1301.3781

  3. Muennighoff, N. et al. (2023). MTEB: Massive Text Embedding Benchmark. arXiv:2210.07316. https://arxiv.org/abs/2210.07316

  4. OpenAI (2024). Text Embedding 3 – Documentation. https://developers.openai.com/api/docs/guides/embeddings

  5. Hendrycks, D. et al. (2021). Measuring Massive Multitask Language Understanding (MMLU). arXiv:2009.03300. https://arxiv.org/abs/2009.03300

  6. Chen, M. et al. (2021). Evaluating Large Language Models Trained on Code (HumanEval). arXiv:2107.03374. https://arxiv.org/abs/2107.03374

  7. Jimenez, C. E. et al. (2024). SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:2310.06770. https://arxiv.org/abs/2310.06770

  8. Artificial Analysis – LLM Performance Comparisons. https://artificialanalysis.ai/

  9. SWE-bench (2026). SWE-bench Verified leaderboard. Reference for the coding scores cited in this module. https://www.swebench.com/ · https://llm-stats.com/benchmarks/swe-bench-verified

  10. Anthropic (2026). Claude – model overview and pricing. Reference for model names, context windows, and token prices. https://platform.claude.com/docs/en/about-claude/pricing

  11. OpenAI (2026). Models – API documentation. Reference for the GPT-6 models (Astra, Sol, Terra, Luna). https://developers.openai.com/api/docs/models/

  12. Cho, A. et al. (2024). Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation. arXiv:2408.04619. The basis for the pipeline and attention visualisations in the "From Prompt to Answer" section. https://arxiv.org/abs/2408.04619

  13. Anthropic (2026). Claude Opus 5 System Card. Vendor figure of around 96 % on SWE-bench Verified (section 8.2). https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf

  14. Anthropic (2026). Thinking – Claude API documentation. Adaptive thinking, effort, and display (defaults to "omitted" on Claude 5 models). https://platform.claude.com/docs/en/build-with-claude/thinking

Further Reading

Transformer Architecture

Embeddings & Benchmarks

Deep Dives