Specialist-model research desk

Do-it-yourself game plans

Sources

Frontier Development research deskSection 02 · Page 15 of 15Last updated 26 October 2026

Evidence boundary: This is desk research and a proposed decision method, not a test of the buyer’s model or an endorsement. Published findings, supplier descriptions and proposed actions are distinguished in the text. Missing private data, quotes and contract terms remain unknown.

TRACE THE EVIDENCE

Sources cited on this page

  1. Demystifying evals for AI agents — Anthropic, 9 January 2026 →www.anthropic.com
  2. Quantization — Hugging Face PEFT documentation →huggingface.co
  3. LoRA Learns Less and Forgets Less — Biderman et al., revision 20 September 2024 →arxiv.org
  4. Pricing — Together AI, snapshot checked 26 October 2026 →www.together.ai
  5. GroupKFold — scikit-learn documentation →scikit-learn.org
  6. A Field Guide to Rapidly Improving AI Products — Hamel Husain →hamel.dev
  7. Guidance on HIPAA & Cloud Computing — HHS Office for Civil Rights →www.hhs.gov
  8. TimeSeriesSplit — scikit-learn documentation →scikit-learn.org
  9. Extend — Extraction Overview →docs.extend.ai
  10. SFT Trainer — Hugging Face TRL documentation →huggingface.co
  11. RouteLLM: Learning to Route LLMs with Preference Data — Ong et al., revision 23 February 2025 →arxiv.org