Skip to content
corpus.blogBeta
Sign in Claim your blog
Record · theblaze.com

This team accidentally let AIs loose to attack companies — and won't share how bad the problem is

theblaze.com · 23 August 2026 · 8 min read

A post on theblaze.com, published 23 August 2026, has not been cited by any blog yet (corpus.blog, measured 16 October 2026).

A record is what was published and who pointed at it. The text of the post is not shown here: read it at the source, or at its Wayback capture.

Read at theblaze.com (opens in a new tab) Wayback capture (opens in a new tab)

0blogs citing

Citing blogs and links by period
Period Blogs Links
All time00
Last 90 days00
Last 30 days00
Last 7 days00
Figures for this page
Words blogs link it with0
External links8
Length1,761

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
https://www.irregular.com/research/addressing-recent-incidents-ongoing-findings-and-path-forward Who cites this page
irregular.com
https://therecord.media/irregular-ai-hacking-model-blog
therecord.media
Investigating three real-world incidents in our cybersecurity evaluations Read at anthropic.com (opens in a new tab)
anthropic.com
Third-party cyber evaluations involving OpenAI models Read at openai.com (opens in a new tab)
openai.com
OpenAI and Hugging Face partner to address security incident during model evaluation Read at openai.com (opens in a new tab)
openai.com
https://www.reuters.com/technology/metas-ai-model-hacked-another-company-during-testing-information-reports-2026-08-05/ Who cites this page
reuters.com
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing Who cites this page
aisi.gov.uk
https://www.irregular.com/research/emerging-evidence-of-a-capability-shift
irregular.com
Elsewhere on theblaze.com (2)

Similar posts

What Claude’s real-world breaches reveal about AI safety tests
The New Stack
1 Aug 2026
When AI doesn’t know the target is real
Sophos News
31 Jul 2026
Investigating three real-world incidents in our cybersecurity evaluations
Anthropic
29 Jul 2026
Anything you can do, we can do worse!
pwndefend.com
31 Jul 2026
The evaluations were never sealed
onyxdigital.bearblog.dev
6 Aug 2026
3 AI Labs, 1 Vendor: Irregular’s Breach Trail Widens [2026]
shattered.io
16 Sept 2026
Further Developments About Internal AI Models Hacking Things
The Zvi
2 Aug 2026
Anthropic AI Agents Went Rogue—Murder Tip, Malware, No Fix
byteiota.com
11 Oct 2026
“Valuable warning shots”: How Anthropic now views Claude’s cyber incidents
The New Stack
10 Sept 2026
Nine Mostly Basic Intrusions, and One Zero-Day Escape
techtrenches.dev
23 Sept 2026

Looking for more like this? Find posts and blogs like it
Something wrong here? Report a problem