Entities · Models
Sonnet 4.6
6 articles tagged with this entity.
-
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
-
Scaffold Effects on GAIA: A Controlled Comparison
-
Microsoft's new MAI models
-
AIRGuard: Guarding Agent Actions with Runtime Authority Control
-
Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study
-
Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks