Mistral Shieldstral changes policy without retraining. The threshold is still yours
Topic
Models
Frontier models, comparisons, and how to choose what fits your work.
28 articles
Models · Page 2
This AutoML benchmark lost 25 points when the clock was enforced
P-Bench shows an AI can run the code and choose the wrong statistical test
A correct SEC answer can cite the wrong company. FinRank measures the evidence error
PAST-Bench makes AI agent memory prove it helped
Lattice static retriever fits in 8 MB. Know what it forgets
Endpoint Accuracy Index: your open model changes with the API
Qwen 3.8 briefly led an agent benchmark. The rerank matters more
AI-designed viruses are real. The headline leaves out the bacteria
Leopold Aschenbrenner’s AI fund story is moving faster than the filings