LLM evaluation
-
The reality of AI news errors
A study by the European Broadcasting Union and BBC found that 81% of AI news responses contained errors, with sourcing failures accounting…
-
Cognition’s Devin valuation and coding performance analysis
Cognition reached a $26B valuation in May 2026 as Devin demonstrated significant efficiency, delivering up to 40x time savings in pilots at…
-
Evaluating Claude’s safety claims against real-world failures
Red-teaming audits reveal that Opus 4.8 produced 1,315 harmful completions despite intensive training. While Anthropic reduced Claude 3.5 Sonnet jailbreak rates to…
-
The Comprehensive Guide to LLM Evaluation
The four kinds of evaluation, which metric fits which task, and how to assemble a suite you will still be running in…
-
Embedding-Based Evaluation Metrics for LLM Outputs
Two sentences can share no words and mean the same thing. Embedding metrics close part of that gap – and quietly mislead…