---
type: "post"
id: "openai-and-poland-s-nask-partner-to-advance-18aeae"
slug: "openai-and-poland-s-nask-partner-to-advance-18aeae"
title: "OpenAI and Poland’s NASK partner to advance AI safety and security"
description: "OpenAI and Poland’s NASK National Research Institute announced an agreement to explore collaboration on AI safety, security and technical research."
retrieval_nugget: "OpenAI and Poland’s NASK National Research Institute announced an agreement to explore collaboration on AI safety, security and technical research."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["security"]
entities: ["OpenAI","NASK National Research Institute","AI Safety Research Center","Polish Artificial Intelligence Safety Institute","CERT Polska","Daybreak","MikroTik RouterOS"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "OpenAI and Poland’s NASK announce a new AI safety and security research partnership, which is not covered by the prior documents."
prior_refs: []
source_url: "https://openai.com/index/openai-nask-ai-safety-security-partnership"
source_urls: ["https://openai.com/index/openai-nask-ai-safety-security-partnership"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:openai-and-poland-s-nask-partner-to-advance-18aeae"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/openai-and-poland-s-nask-partner-to-advance-18aeae/","markdown":"https://newruntime.com/posts/openai-and-poland-s-nask-partner-to-advance-18aeae.md","json":"https://newruntime.com/posts/openai-and-poland-s-nask-partner-to-advance-18aeae.json"}
---

# OpenAI and Poland’s NASK partner to advance AI safety and security

## Retrieval answer

OpenAI and Poland’s NASK National Research Institute announced an agreement to explore collaboration on AI safety, security and technical research.

OpenAI and Poland’s NASK National Research Institute announced an agreement to explore collaboration on AI safety, security and technical research. The announcement is dated October 23, 2026.

NASK’s AI Safety Research Center, which serves as the Polish Artificial Intelligence Safety Institute, and OpenAI say they will work on evaluating increasingly capable AI systems, identifying potential vulnerabilities, and strengthening safeguards. OpenAI describes the arrangement as part of its work with public research institutions and AI safety institutes.

The post also cites an earlier NASK-related activity: in July, CERT Polska, which operates within NASK, received access to OpenAI cyber-capable models through Daybreak. OpenAI says CERT Polska found six vulnerabilities in MikroTik RouterOS, that the vendor issued fixes, and that CERT Polska confirmed those fixes prevented the attacks it had observed.

The source does not establish a budget, duration, research deliverables, evaluation methodology, data-sharing terms, or any new public model, API, or product access.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Security](https://newruntime.com/topics/security.md): Explore the security topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)