corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0d493-f68e-7016-8c79-1135f480d261

Attention Is All You Need: in AI safety too

twelvetables.blog · published 15 September 2026

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

Read the post at twelvetables.blog Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
49
Words captured
4,894

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
OpenAI and HuggingFace: it's about responsibility, not capability Read at the source ↗
twelvetables.blog
https://www.bbc.com/news/articles/c1kx0gyje9wo?ref=twelvetables.blog
bbc.com
OpenAI and Hugging Face partner to address security incident during model evaluation Read at the source ↗
openai.com
OpenAI agents carried out an undisclosed attack on RubyGems Read at the source ↗
rubyhack.ai
https://www.abc.net.au/news/2026-09-12/openai-agents-rubygems-cyber-attack-before-hugging-face-hack/107146386?ref=twelvetables.blog
abc.net.au
Investigating three real-world incidents in our cybersecurity evaluations Read at the source ↗
anthropic.com
The Hugging Face incident and the road ahead Read at the source ↗
openai.com
AI agent collaboration Read at the source ↗
metr.org
Security incident disclosure — July 2026 Read at the source ↗
huggingface.co
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Read at the source ↗
huggingface.co
https://fortune.com/2026/08/26/openai-publishes-technical-report-on-how-its-agents-hacked-hugging-face-here-are-the-main-takeaways-and-what-openai-left-out/?ref=twelvetables.blog
fortune.com
https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/?ref=twelvetables.blog
reuters.com
https://time.com/article/2026/07/24/openai-hugging-face-attack/?ref=twelvetables.blog
time.com
https://www.wired.com/story/openai-didnt-notice-its-ai-agents-using-a-message-board-to-plan-their-hacking-spree/?ref=twelvetables.blog
wired.com
https://openai.com/collective-cyberdefense/?ref=twelvetables.blog
openai.com
https://zeltser.com/media/docs/intro-to-malware-analysis.pdf?ref=twelvetables.blog
zeltser.com
Improving our alignment and security efforts Read at the source ↗
anthropic.com
Previewing GPT-5.6 Sol: a next-generation model Read at the source ↗
openai.com
https://www.infosecurity-magazine.com/news/openai-gpt-5-6-sol-limited-preview/?ref=twelvetables.blog
infosecurity-magazine.com
Daybreak: Tools for securing every organization in the world Read at the source ↗
openai.com
https://siliconangle.com/2026/06/22/openai-expands-daybreak-patch-planet-full-gpt-5-5-cyber-release/?ref=twelvetables.blog
siliconangle.com
https://venturebeat.com/technology/openai-launches-gpt-5-6-cyber-with-reduced-refusals-95-completion-on-advanced-cybersecurity-tasks?ref=twelvetables.blog
venturebeat.com
Cybersecurity in the Intelligence Age Read at the source ↗
openai.com
https://metr.org/blog/2026-06-26-gpt-5-6-sol/?ref=twelvetables.blog
metr.org
OpenAI agent message board Read at the source ↗
collusion.wiki
Safety and alignment in an era of long-horizon models Read at the source ↗
openai.com
https://www.axios.com/2026/07/28/openai-hugging-face-modal-labs-hack?ref=twelvetables.blog
axios.com
https://gvwire.com/2026/09/09/openais-rogue-agents-used-at-least-10-more-sites-for-unauthorized-comms/?ref=twelvetables.blog
gvwire.com
https://fortune.com/2026/09/09/openai-rogue-ai-agents-reached-12-more-websites/?ref=twelvetables.blog
fortune.com
OpenAI admits it didn't disclose rogue AI wiki hijacking incident Read at the source ↗
bleepingcomputer.com
https://betanews.com/article/meta-muse-spark-1-1-security-breach/?ref=twelvetables.blog
betanews.com
https://time.com/article/2026/09/09/ai-anthropic-openai-jacob-coxon/?ref=twelvetables.blog
time.com
https://www.nbcnews.com/tech/security/two-ai-researchers-leave-anthropic-google-safety-concerns-rcna597086?ref=twelvetables.blog
nbcnews.com
https://thenextweb.com/news/pacing-the-frontier-ai-employees-letter-us-government?ref=twelvetables.blog
thenextweb.com
https://www.politico.com/news/2026/07/28/openai-rogue-models-hugging-face-breach-01014572?ref=twelvetables.blog
politico.com
Pacing model development in an era of cyber-critical capabilities Read at the source ↗
openai.com
We must pace the frontier Read at the source ↗
darioamodei.com
https://techcrunch.com/2026/07/22/how-an-openais-human-mistake-led-to-the-ai-powered-hack-on-hugging-face/?ref=twelvetables.blog
techcrunch.com
Piloting the world's first double-blind AI evaluations Read at the source ↗
deepmind.google
https://futureoflife.org/wp-content/uploads/2025/07/Indicator-Survey_Responses_02.pdf?ref=twelvetables.blog
futureoflife.org
https://newsletter.semianalysis.com/p/anthropic-growth-and-bedrock-mix?ref=twelvetables.blog
newsletter.semianalysis.com
https://www.nist.gov/document/aisi-pre-deployment-evaluation-openai-o1-december-2024?ref=twelvetables.blog
nist.gov
https://arxiv.org/pdf/2502.05219?ref=twelvetables.blog
arxiv.org
https://arxiv.org/abs/1706.03762?ref=twelvetables.blog
arxiv.org
https://www.csoonline.com/article/4206116/an-irregular-testing-that-caused-meta-openai-and-anthropic-ai-agents-to-go-rogue.html?ref=twelvetables.blog
csoonline.com
https://lieu.house.gov/media-center/press-releases/reps-lieu-and-moran-introduce-bill-require-kill-switch-ai-systems-can?ref=twelvetables.blog
lieu.house.gov
https://www.citizen.org/news/public-citizen-calls-for-congressional-investigation-following-reports-of-second-company-compromised-during-openai-rogue-ai-incident/?ref=twelvetables.blog
citizen.org
https://www.anthropic.com/news/expanding-project-glasswing?ref=twelvetables.blog
anthropic.com
https://ciaranmartin.substack.com/p/fud-tier-ai
ciaranmartin.substack.com