| ▲ | slopinthebag 9 hours ago | |
Claude Code gets smoked on benchmarks by an agent that has a single tool: tmux. So I think they might actually like that quite a bit. | ||
| ▲ | HarHarVeryFunny 8 hours ago | parent [-] | |
What benchmarks are you referring to? | ||
| ▲ | slopinthebag 9 hours ago | |
Claude Code gets smoked on benchmarks by an agent that has a single tool: tmux. So I think they might actually like that quite a bit. | ||
| ▲ | HarHarVeryFunny 8 hours ago | parent [-] | |
What benchmarks are you referring to? | ||