Hacker News
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computers https://os-world.github.io/ 39 comments
Linking pages
- Notes on Anthropic's Computer Use Ability - Composio https://composio.dev/blog/claude-computer-use/ 113 comments
- Claude just got upgraded, and why you shoud use it over ChatGPT | TalePunk https://talepunk.com/tech/claude-just-got-upgraded-and-why-you-shoud-use-it-over-chatgpt/ 3 comments
- Anthropic Wants Its AI Agent to Control Your Computer | WIRED https://www.wired.com/story/anthropic-ai-agent/ 1 comment
- Claude Sonnet 3.5.1 and Haiku 3.5 - by Zvi Mowshowitz https://thezvi.substack.com/p/claude-sonnet-351-and-haiku-35 0 comments
Related searches:
Search whole site: site:os-world.github.io
Search title: OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
See how to search.