Tag reasonable inquiry

The Most Expensive AI Model Cost Nine Times More. It Wasn't Nine Times More Accurate. Inside Merlin's Automated Test of AI Models for Investigation and Discovery. John Tredennick and Lydia Zhigmitova.

The Most Expensive AI Model Cost Nine Times More. It Wasn’t Nine Times More Accurate. We Tested.

With seven AI models and one assignment, authors John Tredennick and Lydiia Zhigmitova explore validation results around the capabilities of 7 AI models in respect to their accuracy, speed and cost. Anthropic's, Google's and OpenAI frontier models out in September 2026 were tested, including Astra and Fable for citations overall, citations at the paragraph level, fact accuracy and fidelity with surprising results.

Read MoreThe Most Expensive AI Model Cost Nine Times More. It Wasn’t Nine Times More Accurate. We Tested.
Unsupervised Self Collection—The Fox Guarding the Chicken Coop—Leads to Discovery on Discovery

Unsupervised Self Collection—The Fox Guarding the Chicken Coop—Leads to Discovery on Discovery

Michael Berman examines EEOC v. Yas Carib, Inc as an example of the issue of unsupervised self-collection by Defendants. The case covers attorneys as witnesses, "discovery on discovery", technical competence, proportionality and "reasonable inquiry."

Read MoreUnsupervised Self Collection—The Fox Guarding the Chicken Coop—Leads to Discovery on Discovery