A developer built Reward Evidence, a 40-case synthetic benchmark testing whether paid-work assistants can separate cash receipts from opportunity eligibility, and found that GPT-5.4 nano extracted eve…
A developer published a step-by-step guide for building a production-ready deepfake detector in an afternoon, combining a frozen MobileNet-V3 Small backbone with a temporal attention head and packagin…
A developer built Cyber Autopsy, a cyber-forensics investigation system that uses Sanity as a structured content layer and an MCP-compatible server to let an AI reconstruct attack timelines from fragm…
A developer built "The Silent Killer," an adversarial evaluation harness on the Kaggle Model Proxy that tests whether frontier LLMs can audit ML pipelines for fatal methodological flaws rather than sy…
A developer built a Kaggle benchmark that feeds 15 AI models escalating evidence that a supposed practice hacking target is a real company, finding that 73% of answers recognizing the target as real p…
A developer built a 38-case security vulnerability detection benchmark on Kaggle with deliberate false-positive traps to test whether LLMs reason about data flow or merely pattern-match, evaluating 9 …
A developer built a Kaggle benchmark of 336 synthetic Grafana-style monitoring panels to test whether vision models can read dashboards the way an on-call engineer does, grading each model on five fie…
A developer benchmarked four language models on 48 engineering-work logs to test whether they would falsely report "done" when a final check had failed or never ran. Without status definitions, Gemini…
A developer built a benchmark using field data from 123 university students in Goa, India, covering 24 real institutional disputes across education, healthcare, justice and finance to test how frontie…
A developer built the AI Security Stress-Test Benchmark on Kaggle, a 12-task evaluation spanning code vulnerabilities, cloud misconfigurations, and adversarial jailbreaks, and ran six frontier models …
A developer built Cyber Autopsy, a Kaggle benchmark that tests whether AI models can reconstruct reported cyber incidents from partial evidence while citing support for each claim and flagging what re…
A developer built "Repair Without Breaking," a Kaggle Benchmarking Challenge dataset of 60 JSON episodes across 12 graph motifs and five matched conditions (applicable change, no-op, irrelevant update…
A developer built Typic, a 400M-parameter open decision model trained on a single free Kaggle T4 GPU in 46 minutes, which returns probabilities over a supplied list of allowed answers in one forward p…
A developer built a 150-question benchmark from a 7.2M-page web index to measure frontier models' raw parametric knowledge of 2025-2026 events occurring after their training cutoffs. Across nine model…
A developer built Evidence Boundary, a benchmark that tests whether AI models can separate technical exposure findings from authorization scope when triaging synthetic security assessment packets. In …
A developer built Greek Invented Words, a Kaggle benchmarking submission that sends 100 short Greek prompts to 15 language models and scores answers without an LLM judge, using native-speaker verdicts…
A developer built a 200-item benchmark that tests whether language models know when they cannot answer, using an ESCALATE refusal token on one in five items where the answer was deliberately removed. …
A hands-on evaluation of TypeSafe AI's hosted decision model Jev and the open-source alternative Laya found Jev reached 92.3% accuracy on help-desk intent classification and 79.8% on banking intents, …
Fine-tuning an open-source small decision model called Laya raised its accuracy on a banking classification task from 39% to 78%, approaching the 80% scored by TypeSafe AI's Jev, according to the auth…
Asif Waliuddin's Faultline Pro grew from a four-day Kaggle hackathon entry posted December 12, 2025 to 4,887 counted tests by September 30, 2026, after the AI claim checker's Quick Start returned "Moc…