Log inSign up
Amazon Science
Amazon News
7,623 posts
Amazon Science profile banner
@AmazonScience

Amazon Science

Amazon News
@AmazonScience
The latest news and research from Amazon's science community. #AmazonScience
Global
amazon.science
Joined December 2019
1,916
Following
92K
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @AmazonScience
    Amazon Science
    Amazon News
    @AmazonScience
    16h
    Verus is an open-source, automated program verifier for Rust that mechanically checks code against a formal mathematical specification for all possible inputs. Amazon used it to prove correctness of Nitro Isolation Engine primitives.
    Verus-16x9.gif
    Developing provably correct Rust code with Verus
    From amazon.science
    5
  • @AmazonScience
    Amazon Science
    Amazon News
    @AmazonScience
    Aug 28
    When LLM judges agree, the right question is why. Shared prompts, model families, or training lineage can make a majority look stronger than it is. Dependence-aware aggregation via Ising models accounts for this, improving accuracy 9–14% over weighted majority vote.
    agreement_fig1.png
    When LLM judges agree, should we believe them?
    From amazon.science
  • @AmazonScience
    Amazon Science
    Amazon News
    @AmazonScience
    Aug 25
    How did a model upgrade make agents worse? By pairing real enterprise SOPs with functioning tools and ground-truth grading across 12 industries and 2,000+ tasks, SOP-Bench helps find such anomalies.
    Collaborative workflow.16x9.png
    SOP-Bench: A new benchmark for evaluating AI agents on real business procedures
    From amazon.science
  • @AmazonScience
    Amazon Science
    Amazon News
    @AmazonScience
    Aug 11
    Amazon's Automated Reasoning Group started by demoing tools to prove AWS systems secure and correct. A decade later, they have proved the Nitro Isolation Engine, cryptographic code, and S3 correct. Now they are applying the same techniques to AI.
    ARG10Year-Image02-16x9.png
    A decade of mathematical certainty: Reflections on the Automated Reasoning Group
    From amazon.science
    1
  • @AmazonScience
    Amazon Science
    Amazon News
    @AmazonScience
    Aug 10
    📣 AWS Trainium Frontier is open for registration. Train language models from scratch on purpose-built AI chips for @NeurIPSConf. Prizes include $25K for first place, co-publication with Annapurna Labs researchers, and a presentation in Sydney. Deadline is September 30.
    project-rainier-ai-trainium-chips-compute-cluster.png
    AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips
    From amazon.science