Coinbase has fine-tuned an open-weight AI model on its proprietary transaction data to outperform a leading closed-source model in fraud detection, with better detection scores and lower serving latency.<\/p>\n
In a three-part technical series, the exchange argued that companies can get better results from specialized models trained for their own needs than from relying on increasingly capable general-purpose AI systems.<\/p>\n
In an October 12 post, Coinbase CEO Brian Armstrong explained<\/a> that the company has fine-tuned Qwen3.5-9B using internal data and found that it \u201coutperformed frontier models, at much lower cost and speed,\u201d on the specialized task of fraud prevention.<\/p>\n The intended point was not that smaller models are universally better, but that performance depends on the job they are trained to do.<\/p>\n \u201cThe frontier models are amazing generalists,\u201d Armstrong wrote. \u201cBut increasingly you\u2019ll see specialist models out perform on more narrow tasks, either working on teams, or by themselves.\u201d<\/p>\n Coinbase\u2019s Owning Intelligence series described how that approach evolved, with the company first adding an AI risk agent to its existing machine-learning model and rules engine for Onramp, which lets users buy crypto through partner applications, including guest checkout without a Coinbase account.<\/p>\n An online experiment found 30% fewer fraudulent transactions and 22% less fraud value in the group using the additional AI review. The agent examined recent transaction sequences to identify patterns that might not be apparent from a single payment. It could block a transaction that passed the initial checks, but could not reverse an upstream block.<\/p>\n Coinbase then tested newer versions of closed-source models against a fixed benchmark of 16,140 transactions across 7,293 users, including 813 confirmed fraudulent transactions. It reported that newer Opus, Sonnet, and GPT versions performed worse on several fraud-detection measures than their predecessors.<\/p>\n GPT-5.6 improved precision but recorded lower recall, meaning it identified a smaller share of fraudulent transactions. That result motivated the move to an open-weight model, whose parameters could be adapted directly rather than accessed only through a provider\u2019s API.<\/p>\n Coinbase\u2019s approach fits into a wider discussion about AI agents taking on financial crime and security work, with Certik warning<\/a> last week that more autonomous security agents could bring risks from incorrect outputs and reduced human scrutiny. The firm recommended clear limits on autonomous decisions and a named owner for every agent.<\/p>\n However, the crypto exchange\u2019s agent works within such limits, returning a risk score and having application codes that apply the decision policy. It can also block a transaction that earlier checks allowed, but it cannot override a block that\u2019s already been made.<\/p>\n The post Coinbase AI Agent Cuts Fraud by 30% in Onramp Experiment<\/a> appeared first on CryptoPotato<\/a>.<\/p>","protected":false},"excerpt":{"rendered":" Coinbase has fine-tuned an open-weight AI model on its proprietary transaction data to outperform a leading closed-source model in fraud detection, with better detection scores and lower serving latency. In a three-part technical series, the exchange argued that companies can get better results from specialized models trained for their own needs than from relying on […]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-238387","post","type-post","status-publish","format-standard","hentry","category-discovery"],"_links":{"self":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/238387"}],"collection":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=238387"}],"version-history":[{"count":0,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/238387\/revisions"}],"wp:attachment":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=238387"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=238387"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=238387"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Issue Flagged Over AI Autonomy<\/h2>\n