SafetyPublished All news from that day
Ongoing case: Cyber-capable AI models 20 stories
OpenAI signs an agreement with Poland's NASK to explore joint AI safety and security research
The agreement covers research with NASK's AI Safety Research Center; OpenAI says CERT Polska used its models to help find six router vulnerabilities in July.
Check our sources · 5 facts from 1 sourceOpenAI said on 23 October 2026 that it and Poland's NASK National Research Institute have signed an agreement to explore collaboration on AI safety, security and technical research.
Under it, NASK's AI Safety Research Center, which serves as the Polish Artificial Intelligence Safety Institute, and OpenAI will collaborate on AI safety research, including ways to evaluate increasingly capable AI systems and identify potential vulnerabilities.
OpenAI says the agreement builds on work with cyber defenders in Poland. In July, CERT Polska, which operates within NASK, gained access to OpenAI's cyber-capable models through Daybreak, and OpenAI says the team used its models to help discover six vulnerabilities in MikroTik RouterOS. OpenAI says the vendor released fixes, which CERT Polska confirmed prevented the attacks it observed.
Your reaction
We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.
We count reactions per story and day, never who reacted. They help choose what goes in the monthly issue.
Check our sources
Every sentence above is checked against this source.
1 OpenAI and Poland's NASK partner to advance AI safety and security
Open the source archived copy-
OpenAI's post dated October 23, 2026 says OpenAI and Poland's NASK National Research Institute have signed an agreement to explore collaboration on AI safety, security and technical research.
citeOpenAI and Poland's NASK National Research Institute have signed an agreement to explore collaboration on AI safety, security and technical research.
-
The post says that through the agreement NASK's AI Safety Research Center, serving as the Polish Artificial Intelligence Safety Institute (AISI), and OpenAI will collaborate on AI safety research, exploring ways to evaluate increasingly capable AI systems, identify potential vulnerabilities and strengthen safeguards.
citeThrough the agreement, NASK's AI Safety Research Center - serving as the Polish Artificial Intelligence Safety Institute (AISI) - and OpenAI will collaborate on AI safety research, exploring ways to evaluate increasingly capable AI systems, identify potential vulnerabilities and strengthen safeguards.
-
The post says that in July CERT Polska, which operates within NASK, gained access to OpenAI's cyber-capable models through Daybreak.
citeIn July, CERT Polska, which operates within NASK, gained access to OpenAI's cyber capable models through Daybreak.
-
The post says CERT Polska's team used OpenAI models to help discover six vulnerabilities in MikroTik RouterOS, including flaws that could be combined to take control of affected devices without authentication.
citeThe team used OpenAI models to help discover six vulnerabilities in MikroTik RouterOS, including flaws that could be combined to take control of affected devices without authentication.
-
The post says the vendor released fixes, which CERT Polska confirmed prevented the attacks it observed.
citeThe vendor released fixes, which CERT Polska confirmed prevented the attacks it observed.
Every sentence above is checked against this source. Each fact has its own address you can cite.
Source 1 · OpenAI · 23 Oct 2026
OpenAI and Poland's NASK partner to advance AI safety and security
OpenAI's post dated October 23, 2026 says OpenAI and Poland's NASK National Research Institute have signed an agreement to explore collaboration on AI safety, security and technical research.
OpenAI and Poland's NASK National Research Institute have signed an agreement to explore collaboration on AI safety, security and technical research.
The post says that through the agreement NASK's AI Safety Research Center, serving as the Polish Artificial Intelligence Safety Institute (AISI), and OpenAI will collaborate on AI safety research, exploring ways to evaluate increasingly capable AI systems, identify potential vulnerabilities and strengthen safeguards.
Through the agreement, NASK's AI Safety Research Center - serving as the Polish Artificial Intelligence Safety Institute (AISI) - and OpenAI will collaborate on AI safety research, exploring ways to evaluate increasingly capable AI systems, identify potential vulnerabilities and strengthen safeguards.
The post says that in July CERT Polska, which operates within NASK, gained access to OpenAI's cyber-capable models through Daybreak.
In July, CERT Polska, which operates within NASK, gained access to OpenAI's cyber capable models through Daybreak.
Show all 5 factsShow fewer facts
The post says CERT Polska's team used OpenAI models to help discover six vulnerabilities in MikroTik RouterOS, including flaws that could be combined to take control of affected devices without authentication.
The team used OpenAI models to help discover six vulnerabilities in MikroTik RouterOS, including flaws that could be combined to take control of affected devices without authentication.
The post says the vendor released fixes, which CERT Polska confirmed prevented the attacks it observed.
The vendor released fixes, which CERT Polska confirmed prevented the attacks it observed.
Topics
The morning email
On the mornings we publish: the three top stories and up to four short ones. Free.
We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep