#LLM Evaluation

4 articles with this tag

LLM Drift: A Structural Blind Spot
AI Research

LLM Drift: A Structural Blind Spot

LLMs suffer from structural temporal drift, rendering them confidently outdated. A new geometric probe detects this, outperforming standard methods.

7 days ago
LLMs Fail Esoteric Code Tasks
AI Research

LLMs Fail Esoteric Code Tasks

Frontier LLMs show a dramatic capability gap on a new benchmark using esoteric programming languages, revealing a reliance on memorization over reasoning.

2 months ago
Balyasny's AI Engine
Artificial Intelligence

Balyasny's AI Engine

Balyasny Asset Management built a powerful AI research engine using OpenAI models, slashing analysis times and boosting investment team confidence.

2 months ago
Context-Aware Guardrails Tested
Technology

Context-Aware Guardrails Tested

Mozilla.ai tested context-aware guardrails for LLMs in a humanitarian context, revealing crucial multilingual performance disparities and the need for robust, domain-specific safety policies.

3 months ago