Powerful open models can be trained for a range of safety and security challenges without compromising capability. Inflection AI and AI21 post-trained NVIDIA Nemotron open models with Alice’s safety data, demonstrating a path to responsibly deploying customizable AI.

NEW YORK, Oct. 15, 2026 (GLOBE NEWSWIRE) -- Alice announced the results of two collaborations focused on aligning NVIDIA Nemotron models to company-specific safety and security policies. The results demonstrate how real-world threat data can be used to train open-source models for frontier safety performance. 

Open-source models give organizations greater control over AI behavior, allowing them to train policies into the underlying model rather than setting instructions as system prompts. To successfully train models on their policies, companies need adversarial data and expertise. Two projects demonstrate how NVIDIA’s state-of-the-art open-source model can be aligned for safer human interactions, and more secure enterprise agents. 

“Powerful AI is being democratized. It’s now available to companies everywhere, and they want to use it safely and predictably,” said Noam Schwartz, CEO and co-founder of Alice. “These results show that with the right real-world adversarial data and training, we can teach open source models how to handle the threats and abuse they will actually face, across very different safety challenges, while keeping them as powerful. That's the bar now: frontier-grade safety that any organization running advanced AI can actually put into practice.”

Training safety for how people actually use AI

Inflection AI is building personal AI that empowers people and shifts interactions from transactional to relational. Allowing more natural interactions with conversational AI also increases risks which most benchmarks can’t catch. In the process of building the next generation of personal intelligence, Inflection AI fine-tuned NVIDIA Nemotron 3 Super 120B-A12B, and turned to Alice to develop red-teaming datasets aimed at reducing sycophancy and preventing the model from reinforcing unhealthy attachment over long conversations. Fine-tuning on that data raised Pi’s alignment score by 30% while keeping unnecessary refusals to just 1.6%.

Alice created more than 20 realistic personas and used them in multi-turn red-team exercises where those risks could develop over time. The personas included vulnerable but benign users as well as adversarial users deliberately attempting to manipulate the model, drawing on Alice’s real-world knowledge of harmful and adversarial behavior.

“As AI innovation accelerates, safety has to advance rapidly as well. It’s no longer enough to ask whether a model can identify and refuse a harmful prompt,” said Sean White, CEO of Inflection AI. “We also need to understand how AI behaves across hundreds of interactions, whether it challenges rather than simply agrees, if it supports human agency rather than dependency, and ultimately if it leaves people more capable. This work with Alice and NVIDIA demonstrates that we can train those principles into powerful open models without sacrificing what makes them useful. That’s fundamental to the kind of human-centered Personal Intelligence we’re building with Pi.”

Security without sacrificing capability

Alice also worked with AI21, which has trained language models since 2021 and now offers lab-as-a service for specialized intelligence. The work with them focused on a very different problem: protecting enterprise agents against indirect prompt injection. As agents gain access to company systems, data and tools, attackers can attempt to manipulate them through information the agent encounters while doing its work. Training against those attacks therefore cannot focus only on whether the model refuses a malicious instruction. A secure agent also needs to recognize the attack while continuing to complete the legitimate task.

Alice’s reinforcement-learning environments were built to train and measure both. AI21 used them to post-train the recently released NVIDIA Nemotron 3.5 Super VL open model, increasing the model’s resilience to indirect prompt injection by 41 points, competing with GPT-6.1 Sol.

The result shows that security and capability are not necessarily competing objectives. With the right training, models can become significantly more resilient to adversarial manipulation while maintaining task performance.

"For most companies, the next phase of AI adoption goes beyond frontier models, to open models they own, shape and control," said Ori Goshen, Co-founder and CEO of AI21. "Owning a model means owning how it fails, not only what it can do. We post-trained NVIDIA Nemotron 3.5 Super-VL on attack traces Alice sees in the wild, so it holds up against the attacks that actually reach enterprises while keeping the behavior it was built for."

“NVIDIA Nemotron provides the open weights, recipes and tooling for organizations to post-train on their own data and optimize accuracy and performance for their specific workloads,” said Joey Conway, senior director Nemotron and Software, NVIDIA. “Alice’s work with Inflection AI and AI21 shows how post-training Nemotron on real-world adversarial data delivers powerful safety and security — exactly the kind of innovation open models are meant to unlock.”

Taken together, these collaborations demonstrate how real-world adversarial intelligence, safety datasets, expert red teaming and reinforcement-learning environments can turn open models into systems trained for the risks they will actually face. The broader opportunity is clear: powerful, customizable AI that companies can own and deploy with frontier-level safety built in.

About Alice

Alice is an AI safety and security company helping model builders and enterprises train, evaluate, and deploy safer AI. Its adversarial intelligence combines continuously emerging threats from open and closed communities with expert research to power red teaming, evaluations, training data, RL environments, and enterprise guardrails. Alice works with 8 of the 10 leading foundation model labs and AI-native companies, while helping enterprises test and protect AI applications against real-world safety and security risk.

About Inflection AI 
Inflection AI is a Public Benefit Corporation with the mission to harness the power of AI to improve human well-being and productivity. Inflection AI is empowering people and brands with human-centered, emotionally intelligent AI that transforms interactions from transactional to relational. Inflection AI pioneered Personal Intelligence with Pi, the world's first Personal Intelligence partner, built to help people navigate their lives. Pi is powered by the Inflection AI stack orchestrated across custom fine-tuned models. 

About AI21

AI21 is an AI lab building frontier models and AI systems for the enterprise since 2017. Creator of the Jurassic and Jamba model families, AI21 today offers its lab-as-a-service for specialized intelligence: Forward-Deployed Researchers and a harness- and model-training platform that turn open foundations into models its customers own, delivered with the weights, recipes and evaluations that keep them theirs.  AI21 has secured $336 million in funding from industry leaders, including Google, and Intel, reinforcing its commitment to advancing AI innovation. 

CONTACT: Media Contact:
Mark Prindle 
mark.prindle@fusionpr.com