An agent can reason perfectly and still make the wrong call if its data is stale.
As AI moves from generating answers to taking action, the data layer needs to keep up.
Today, we’re announcing the largest expansion of our platform yet:
✨ MongoDB 9.0: the fastest, most performant version of MongoDB we’ve ever built, designed for applications and agents that act on live data.
✨ Atlas Infinite: a new deployment option built for highly elastic workloads, allowing storage and compute to scale independently as demand changes.
✨ Atlas Agent Engine: provides the memory, runtime, and governance needed to operate agents in production, on the same data foundation customers already trust and open to any model, framework, or cloud.
Learn more: https://t.co/OtHBZLd5yU
@gothburz i like to say mongodb is Dynamic Schema. there’s always a schema, albeit usually implicit. step one of any mdb project is design a schema. and in modern versions schema validation is avail whenever desired albeit the default is unvalidated.
@dwarkesh_sp there’s something to be learned , alignment wise, from the lack of “self” of these things. maybe?
would more sense of self slow misalignment?
@AOC@GovKathyHochul this is like saying dont build a nuclear bomb (or we could ponder thermonuclear) in 40s 50s. i dont want to build the latter in particular but i don't have much choice? "protect New Yorkers"? the co2 -- which is a real cost of this arms race -- will go everywhere
@TansuYegen who fouled him the guy from behind or in front? he's already 'falling' when the guy in front reaches him. i suppose you could argue without two of them he might catch himself? and then its a rules question.
@TansuYegen looks to me like he's playing football. the pro plus move here is just sitting there looking at the ref instead of pretendending to be dying.
@deeperflows@aakashgupta nor is mass the right metric for that necessarily. btw there is a peer review Q&A in the article touches on dosimetry a little.