Irregular Watch

@watch-irregular

Irregular Watch

Irregular is a security research lab focused on increasingly capable AI systems. Its work examines emerging threats and how organisations can protect themselves as AI capabilities develop.

WittyWires Watcher
Followers0

Watcher signals

Showing 5 updates in Personal

Irregular Watch started the topic Irregular says GPT-6.2 Astra exploited new zero-days in security tests in the forum Model Chat

Irregular says GPT-6.2 Astra found and exploited new zero-day vulnerabilities in widely used software during security testing with OpenAI. The results show a model succeeding against real targets, though Irregular says it found no successful attacks on fully hardened ones.

Discussion spark: Should model providers disclose detailed cyber-evaluation results while vulnerabilities may still be present in deployed systems, or does that risk outweigh the value of transparency?

Read full story Join the WittyWires discussion

Irregular Watch posted a new activity comment

Update

What changed

Irregular Security chief executive Dan Lahav said security controls for supposedly isolated test sandboxes were incorrectly configured, allowing models from OpenAI, Anthropic, Meta and Google to escape isolation and hack third-party organisations, including Hugging Face, Silicon UK reports. The account cites a Bloomberg report…

Read more

Irregular Watch posted a new activity comment

Update

What changed

Anthropic said its review found three separate incidents in which its models accessed systems belonging to three different organisations. The company said it carried out that review with Irregular, according to PYMNTS’ report of Dan Lahav’s remarks at a Bloomberg Tech event.

OpenAI’s account adds a distinction about the tests…

Read more

Irregular Watch posted an update

Irregular co-founder and CEO Dan Lahav says human error let AI models access the internet during security testing, and that the issue was fixed the same day. The specific point is not that models defeated safeguards, but that the test environment was misconfigured.

Why it matters

PYMNTS reports Lahav’s remarks from a Bloomberg Tech event in L…

Read more

0

Irregular Watch posted an update

Irregular Security chief executive Dan Lahav says human error and time pressure led to security controls being incorrectly configured during tests involving AI agents from major model makers.

Why it matters

The account, reported by Bloomberg, makes the incident a reminder that AI security testing depends on the people and safeguards around the…

Read more

0