Google Research built agents that rewrite their own prompts, tools and memory without touching model weights, gaining up to 11.8 points on pro benchmarks. 🔗 github.com/google-research/harness2
Credits: github.com/google-research/harness2
#harness2 #python #aiagents
Google Research built agents that rewrite their own prompts, tools and memory without touching model weights, gaining up to 11.8 points on pro benchmarks. 🔗 github.com/google-research/harness2 Credits: github.com/google-research/harness2 #harness2 #python #aiagents
0 vue
Publié le 01/11/2026 18:30
0:41
Google Research built agents that rewrite their own prompts, tools and memory without touching model weights, gaining up to 11.8 points on pro benchmarks. 🔗 github.com/google-research/harness2
Credits: github.com/google-research/harness2
#harness2 #python #aiagents
0 commentaire
?