CITATION — REFERENCE ENTRY
eval-caveats · almeida2026introducing
- Citation
- almeida2026introducing
- Claim ID
- eval-caveats
- Assertion
- TypeSafe discloses that its workflow evaluations were written by its own capabilities team; that reference answers were the average of GPT-6 Astra and Fable 5.1, which may favour OpenAI and Anthropic models; that LLMs were run through TypeSafe's own wrapper constraining them to structured decisions; that latency was largely measured from West Coast laptops; and that it cannot prove its pricing is not subsidised.
Available in