Stories by reshabh

GitHub Models CLI now auto-generates test cases and an evaluator

Testing AI Software Isn't Like Testing Plain Old Software

PromptPex: Automatic Test Generation for Language Model Prompts

How to Hack AI Agents and Applications

2025 Top Risk and Mitigations for LLMs and Gen AI Apps

Software Security Analysis in 2030 and Beyond: A Research Roadmap

SPML: A DSL for Defending LLMs Against Prompt Attacks

GWP-ASan: Sampling-Based Detection of Memory-Safety Bugs in Production