Agents6d ago
Alibaba Tongyi-MAI Releases OpenGCUA and MAI-Gym: Full Open Stack for Generalist Computer Use Boosts OSWorld-v2 by +19.6 Points and Cuts Steps by 53%
Alibaba's Tongyi-MAI team has open-sourced two foundational frameworks for generalist computer-use agents: OpenGCUA (arXiv:2610.22200) and MAI-Gym (arXiv:2610.20939). By unifying GUI interaction with programmatic code execution and harness-to-model decision transfer, OpenGCUA elevates scores on OSWorld-v2 across all eight tested models—including GPT-6 Astra and Claude Opus 5—by +19.6 points while cutting steps by 53.0%. Meanwhile, MAI-Gym scales online RL to 20,000 parallel instances, training MAI-Gym-9B to 78.4% on MobileWorld and 76.2% on OSWorld-Verified.
Product1d ago
ChatGPT Officially Rolls Out Locked Chats: Biometric Authentication and Complete Memory Isolation Across All Tiers
OpenAI officially rolled out 'Locked Chats' across all ChatGPT subscription tiers, including Free, Plus, Team, Enterprise, and Edu. Users can now safeguard sensitive individual conversation threads behind a device PIN, Face ID, or Touch ID biometric lock. Crucially, locked chats feature strict memory isolation: interactions inside locked sessions are physically barred from updating ChatGPT's persistent user memory bank. Confidential corporate discussions, sensitive health queries, or proprietary code audits remain strictly ephemeral to the local lockbox without contaminating future general chat contexts.
Release47d ago
Perplexity Computer: Pro and Max get both Fable and Astra
Perplexity CEO Aravind Srinivas confirmed Pro and Max subscribers can use both Claude Fable and GPT-6 Astra in Perplexity Computer mode. After Astra landed on Computer, this makes dual frontier-model choice explicit for coding, computer-use, and research workflows.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.