이원화된 레이어 설계로 Mind2Web 벤치마크 81% 달성
OpenAI Operator scores 43% on hard web tasks. We scored 81%. Here are all 300 runs.
OpenAI Operator scores 43% on hard web tasks. We scored 81%. Here are all 300 runs.
llama.cpp supports Sparse MoE, new Qwen3.6 GGUF, & WebWorld for local agents
You've Never Seen 90% of the Internet. Neither Has Google.
Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H