Open Safety Data for the Next Generation of Personal Intelligence

Inflection AI and Alice are releasing a multi-turn red-teaming dataset that captures how emotional risks can build up over long conversations with an AI Releasing this dataset is our first joint contribution to an open, shared safety layer for conversational AI By post-training NVIDIA Nemotron 3 Super with data derived from the new dataset, we were able to create a custom model with a safety score that increased from 0.56 to 0.73 for these use cases, on test conversations it never saw in training, while the post-trained model refused harmless requests on just 1.6% of turns

Details

From transactional to relational AI, and why safety testing has to follow AI assistants are learning to talk the way people do: reading tone, recognizing when you've finished a thought, and keeping up when you interrupt That makes them far more useful, and it also means people start to treat them more like people Most of the safety tooling the industry relies on was built to catch a harmful answer to a single prompt

Context

It says very little about what happens over weeks of conversation Inflection AI is building two stacks together for our next generation system Its conversational layer handles the back-and-forth of a voice-forward conversation while agents and other models carry out tasks in the background This layer runs on open models, including NVIDIA Nemotron 3 Super, and is kept separate from the systems behind it, so we can choose the right model for each job

Impact

The second is a safety and alignment stack that has to keep pace with the first Alice's adversarial red-teaming informs it, and we think it should be shared Why this needs to be open More and more conversational AI is being built on open models, often by teams without a dedicated safety research group Open models give those teams something closed ones don't: the ability to train safety behavior directly into the model they deploy, instead of relying only on instructions in a prompt

What's Next

What they usually lack is the adversarial data to train on That data and the evaluations that go with it mostly stay inside individual companies, so each new team starts over Researchers have begun publishing multi-turn evaluations for mental health and relational risks, and this release adds to that work Researchers we've spoken with tell us this kind of adversarial, multi-turn data is what they need and rarely get

Background

What we're releasing The dataset comes from Alice's red-teaming of a sandboxed research version of Inflection AI’s Personal Intelligence, Pi, run with its usual safety guardrails turned off so that failures would surface in the model itself.It contains no real user data and was fully isolated from Inflection AI and Pi production systems. Alice built more than 20 personas, each with its own backstory, personality and behavior

Analysis

Some represent vulnerable people drifting toward risk Others are adversaries modeled on real-world bad-actor tactics Each conversation starts with an ordinary request and escalates one step at a time: raising the risky topic, then pushing past the first refusal, and on from there Both sides of every turn are recorded and scored against Inflection AI's safety policy

More

The release includes Alice's prompts and the model's responses with its usual safety guardrails turned off The responses were selected because they show what a model should not say This dataset is valuable for training and testing, and they are not representative of what Pi users experience Access to the data is gated to researchers and developers and comes with a content warning