Grounded or Gamed? We Audited Our Own Cyber Benchmark
Our benchmark tests whether LLMs reason about IDOR vulnerabilities or just pattern-match. They're grounded — but every model still misses 70% of real bugs.
London calling: Highlights from the 2025 cloud & cyber security expoSemgrep
Boosting Security Scan Performance for Monorepos with Multicore Parallel ProcessingSemgrep
Beyond Benchmarks: How Semgrep Redefines Javascript SecuritySemgrep
Benchmarking Semgrep Community Edition Performance ImprovementsSemgrep
Beyond vulnerabilities: Detect malicious dependencies in your supply chainSemgrep
From Gatekeepers to Guardrails: Automating Your PCI DSS v4.0.1 StrategySemgrep
A Guide to Extended Threat Detection and Response: What It Is and How to Choose the Best SolutionsCybersecurity Exchange
Security Considerations for API-Driven Apps Deployed to CloudThenewstack
How to Use Your Own RegistryDocker
Build Your Own PluginVercel
Lies, damn lies, and benchmarksDeepgram
Be the Hero in Your Real-Life Cyber Heist ScriptThenewstack
Beating proprietary models with a quick fine-tuneModal
Modal Clusters are generally availableModal
Bits InvestigationDatadoghq
Using MotherDuck at MotherDuck: Loading Data from Postgres with DuckDBMotherduck
Storage Structure - bunny.net DocumentationBunny
Build your own AI app builder with the v0 Platform APIVercel
Reverse proxy - MintlifyMintlify
SuperGLUE: Understanding a Sticky Benchmark for LLMsDeepgram
