you are right that a traditional fuzzer (especially a grey-box one like AFL or a white-box one) is superior in speed, cost per execution, and comprehensiveness.
The argument for using an LLM to generate a curated set of fuzz inputs isn't to replace traditional fuzzers, but to complement them by targeting a different class of bugs that traditional fuzzers are often poor at finding.
The goal of this tool is two fold.
1. give LLMs the ability to make use of traditional software testing tools
2. enhance some of the shortcomings in traditional software testing tools by selectively using LLMs (specifically their ability to understand the larger context the code is written in)
With Black populations of 15M-30M in US during that period, that means 3M-7M counterexamples to the implication that was impossible to be an American homeowner in your 20s (or child living in a home) if “your skin was black or brown”. At least in the late 1900s.
Since you referred to America as “there”, I have to assume you don’t live in the US. You can do basic online research, though. Please present contrary evidence if you have it.
It was relatively easy to own homes in rural and semi rural America in the 1900s no matter who you were. The communities might have been segregated, but one of the most charming neighborhoods I discovered while biking on the East Coast was a small rural Black village hidden back off the main road. It was like going back in time 80 years. Slow-paced, modest, quiet…a real gem. Guessing they wouldn’t have wanted a White boy there, though.
Hey, I’m part of the Kodus team. We built an open source code review agent. It’d be awesome if you gave it a try. Here’s the repo (https://github.com/kodustech/kodus-ai)
I also wish that I had more real world experience. It would help me a ton if I had 25 years of software testing experience.
It sounds like you do have experience, and I would love to learn from you. It would be awesome if you could help us build a tool that is truly useful for you and your work.
That is one of the obvious use cases. There are many others, you are welcome to install the bot and play around with it. I would love to hear your feedback.
The bugs shown in the "real bugs" section are real output from the tool. Are you referring to looking at the full table of bugs that we return? Sometimes we only find one bug in the PR, sometimes our clients don't want us to share other bugs that could expose their work.
The argument for using an LLM to generate a curated set of fuzz inputs isn't to replace traditional fuzzers, but to complement them by targeting a different class of bugs that traditional fuzzers are often poor at finding.
The goal of this tool is two fold.
1. give LLMs the ability to make use of traditional software testing tools
2. enhance some of the shortcomings in traditional software testing tools by selectively using LLMs (specifically their ability to understand the larger context the code is written in)