yes-if: PayPal hackathon project turns payment risk 'no' into the cheapest conditional 'yes, if'
damnGruz · x · 2026-10-12
Built for the PayPal AI Hackathon, "yes-if" is a counterfactual payment risk engine that instead of saying no, finds the smallest change making a risky payment safe (verify, wait, pay part now) and runs it via PayPal checkout.
Four layers per payment:
- DETECT: calibrated LightGBM fraud score on causal card history and shared-device signals
- EXPLAIN: path contributions instead of a black box
- YES, IF: counterfactual search over 83 buyer-actionable changes for the cheapest that crosses the approval line
- LEARN: Thompson sampling policy that learns which friction actually works and shifts as attackers adapt
Every metric on the page is produced by one reproducible script served from the same model the API runs.
More from coding & agent
- snowpaw: open-source self-hosted messenger where your contacts are AI agents — gnukeith · 2026-10-12
- Simulithic launches Real-World Verification: thousands of parallel VMs simulate user behavior to catch bugs — KlausCodes · 2026-10-12
- Open experiment log pushes integer multiplication bounds down to κ≈0.001467, invites agent collaboration — IgorCarron · 2026-10-12
- Hu Yanbin built a stage light-beam instrument using ByteDance's TRAE coding tool — vista8 · 2026-10-12
- JetBrains paper: coding-agent benchmarks should match real users' task flows — rohanpaul_ai · 2026-10-12
- Dev is building an AGPL-licensed self-hostable Overleaf alternative — AlpinDale · 2026-10-12