Tag: llm

All the articles with the tag "llm".

• The retrieval test passed. The refusal checker could not prove the assistant stopped

  Published: 22 Sep, 2026

  • 6 min read

  A technical account of multilingual RAG evaluation, unsupported questions, and why a refusal phrase cannot prove the assistant stopped.

• My assistant answered a question without supporting evidence

  Published: 22 Sep, 2026

  • 2 min read

  Three models found the expected documents. Unsupported questions exposed a separate requirement: stop when the knowledge base has no answer.

• Claude Fable 5 refused my defensive security review

  Published: 11 Jun, 2026

  • 3 min read

  Claude Fable 5 refused a defensive review of our own SaaS application twice, including a prompt that explicitly banned exploit guidance.

• The token tax of Norwegian Bokmål in LLMs

  Published: 5 May, 2026

  • 2 min read

  The same government foreword used 37.4% to 67.5% more tokens in Norwegian Bokmål than in English, despite fewer characters.