Active Memory

Headlines · 2

1. 4d
   Meta ships Muse Wonder-trained specialized models to Muse and Meta AI

   Meta announced on November 6 that specialized models trained with its frontier Muse Wonder series are now rolling out to Muse and Meta AI, bringing over the Active Memory and Active Focus capabilities first introduced with Muse Wonder. Meta says Active Memory helps models recognize when earlier information still matters and separate it from stale context, while Active Focus helps them recover from setbacks or find alternatives when constraints change. Meta's internal evaluations report a 2.4x reduction in forgetting goal-critical information, a 67% improvement in getting unstuck as constraints evolve, 90% correct use of critical context versus 76% for previous models, and a Personal Superintelligence Index score of 47% up from 38%.

   AI at Meta (X) · 🔥 6
2. Oct 12
   Meta Unveils Muse Models After Revealing $100B–$200B AI Infrastructure Commitment

   Mark Zuckerberg said in a Bloomberg report that Meta committed to spending $100 billion or $200 billion on AI infrastructure in 2025 before it knew whether its AI products would succeed. Separately, Meta announced Muse Wonder and Muse Wonder Full, describing them as its most capable models to date for coding, complex reasoning, autonomous tasks, document analysis and financial research. Muse Wonder is available through Meta’s Model API and Muse Code, while Muse Wonder Full is limited to Muse Code subscribers; Meta has not announced separate API access for the latter.

   36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my Active Memory experienceAsk about Active Memory