Rage4J surfaces on Hacker News: LLM app testing for Java
Muteval is a tool that applies mutation testing to LLM evaluation suites, helping developers assess the quality of their evals by introducing small changes (mutations) to test data or prompts and checking whether the eval catches them. It solves the problem of untrustworthy LLM evals by revealing blind spots and overfitting.
Muteval is a tool that applies mutation testing to LLM evaluation suites, helping developers assess the quality of their evals by introducing small changes (mutations) to test data or prompts and checking whether the eval catches them. It solves the problem of untrustworthy LLM evals by revealing blind spots and overfitting.
PromptTrace provides free, interactive labs where users can practice prompt injection and other LLM security attacks. It helps developers and security researchers understand and defend against LLM vulnerabilities through hands-on exercises.
PromptTrace provides free, interactive labs where users can practice prompt injection and other LLM security attacks. It helps developers and security researchers understand and defend against LLM vulnerabilities through hands-on exercises.
A prompt that instructs large language models to generate property-based tests for code. It helps developers automatically create more robust tests by leveraging LLMs to produce test properties, reducing manual effort in test generation.
A prompt that instructs large language models to generate property-based tests for code. It helps developers automatically create more robust tests by leveraging LLMs to produce test properties, reducing manual effort in test generation.
Litelm: LiteLLM Without the Bloat
Litelm: LiteLLM Without the Bloat
Sentrint is a security scanner designed for projects built with LLMs. It helps developers identify vulnerabilities specific to AI-generated code, addressing the unique security challenges introduced by LLM-assisted development.
Sentrint is a security scanner designed for projects built with LLMs. It helps developers identify vulnerabilities specific to AI-generated code, addressing the unique security challenges introduced by LLM-assisted development.