11. To quantify how the models handle unfamiliar tasks, we compared test-time compute scaling on tasks t... To quantify how the models handle unfamiliar tasks, we compared test-time compute scaling on tasks trained on during post-training against other tasks. Both models improve similarl 10/13 01:29 ♡
12. Delivering personal superintelligence requires a significant investment in alignment and safety, and... Delivering personal superintelligence requires a significant investment in alignment and safety, and demands a model that exercises discretion with private information and resists 10/13 01:02 ♡
13. W We hope that Muse Wonder and Muse Wonder Full give more people the power to pursue their dreams and ... We hope that Muse Wonder and Muse Wonder Full give more people the power to pursue their dreams and build the world they want. Learn more in our research blog: go.meta.me/musewonde 10/13 01:02 ♡
14. Two things make Muse Wonder suited for long-running, multi-step work an agent faces every day: -> A... Two things make Muse Wonder suited for long-running, multi-step work an agent faces every day: -> Active Memory carries your context across conversations and surfaces it when it 10/13 01:02 ♡
15. The Muse Wonder series achieves state-of-the-art results across key benchmarks for personal and prof... The Muse Wonder series achieves state-of-the-art results across key benchmarks for personal and professional agents, memory, and coding. Muse Wonder and Muse Wonder Full apply spec 10/13 01:02 ♡
16. W We’re excited to introduce the Muse Wonder series with Muse Wonder and Muse Wonder Full, our most ca... We’re excited to introduce the Muse Wonder series with Muse Wonder and Muse Wonder Full, our most capable models yet. Both are frontier models, built to deliver state-of-the-art pe 10/13 01:02 ♡
17. 6 6️⃣ Non-Associative Algebra: The team worked with Muse Spark to find an exception to a proposed rule... 6️⃣ Non-Associative Algebra: The team worked with Muse Spark to find an exception to a proposed rule about mathematical structures inspired by biology. They went further by develop 10/03 03:11 ♡
18. R Read more on our research blog: https://t.co/J0e9snbE8Q Read more on our research blog: research.meta.ai/blog/solving-o… 💬 4 🔄 4 ❤️ 74 👀 14461 📊 13 ⚡ Powered by xgo.ing 10/03 03:11 ♡
19. 1️⃣ Probability: Mathematicians worked with Muse Spark to answer a question about fitting random po... 1️⃣ Probability: Mathematicians worked with Muse Spark to answer a question about fitting random points onto the surface of a stretched sphere. For the setting studied, they proved 10/03 03:11 ♡
20. F Following gold-medal-level performance from our AI models across five competitions in mathematics, p... Following gold-medal-level performance from our AI models across five competitions in mathematics, physics, and chemistry, we asked a harder question: can AI contribute when a prob 10/03 03:11 ♡
