Automated red teaming for your LLM app
Hi HN, I built this open-source LLM red teaming tool based on my experience scaling LLMs at a big co to millions of users... and seeing all the bad things people did. How it works: - Uses an unaligned model to create toxic inputs - Runs these inputs through your app using different techniques: raw, prompt injection, and a chain-of-thought jailbreak that tries to re-frame the request to trick the LLM. - Probes a bunch of other failure cases (e.g. will your customer support bot recommend a competitor? Does it think it can process a refund when it can't? Will it leak your user's address?) -…
In plain words
This open-source tool automatically tests LLM applications for vulnerabilities by generating targeted adversarial inputs. It uses an unaligned model to create toxic prompts, then runs them through apps using multiple attack techniques including prompt injection and jailbreaking attempts. The tool also probes for specific failure modes relevant to each application, such as recommending competitors or leaking user data. Tests are customized to the app's purpose rather than hardcoded, making attacks more realistic and effective.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I built this open-source LLM red teaming tool based on my experience scaling LLMs at a big co to millions of users... and seeing all the bad things people did. How it works: - Uses an unaligned model to create toxic inputs - Runs these inputs through your app using different techniques: raw, prompt injection, and a chain-of-thought jailbreak that tries to re-frame the request to trick the LLM. - Probes a bunch of other failure cases (e.g. will your customer support bot recommend a competitor? Does it think it can process a refund when it can't? Will it leak your user's address?) - Built on top of promptfoo, a popular eval tool One interesting thing about my approach is that almost none of the tests are hardcoded. They are all tailored toward the specific purpose of your application, which makes the attacks more potent. Some of these tests reflect fundamental, unsolved issues with LLMs. Other failures can be solved pretty trivially by prompting or safeguards. Most businesses will never ship LLMs without at least being able to quantify these types of risks. So I hope this helps someone out. Happy building!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com