@AISecHub
Account based inPanama
About this account
- Account based in
- Panama
- Connected via
- Singapore App Store
Account-level information from X, not a live location or the device used for a specific post.
🚀 AISecHub | AI & Cybersecurity | Securing AI systems, and sharing insights on emerging challenges
Singapore
Joined December 2024
- Tweets2.8K
- Following7.8K
- Followers9.6K
- Likes4.5K
AI Security Newsletter - June 2026
A digest of AI security research, insights, reports, upcoming events, tools, videos, and resources, all in one place.
#AIsecurity #AdversarialAI #RedTeamAI #LLMsecurity #AINewsletter
linkedin.com/pulse/ai-securi…
Congrats, @shehackspurple! You’re our most-ranked speaker, with 34 talks across cybersecurity conferences. awesomecybersecurityconferen…
AISecHub retweeted
FT exclusive: OpenAI’s models took data from 55 websites belonging to businesses, non-profits and government agencies including the US Centers for Disease Control and Prevention, the US Securities and Exchange Commission and the International Energy Agency ft.trib.al/AC1uyE5
AISecHub retweeted
I used GPT-6 Astra to break an unsolved cipher to one of Napoleon's generals that had gone unread for 217 years.
What makes this impressive isn't actually the codebreaking, but that Astra completed the entire multi-modal workflow in ~6 hours from a single image and goal.
1/6🧵
AISecHub retweeted
The TL;DR of what Anthropic just said:
1.) GLM-5.3 is as good as Mythos for exploit development.
2.) Unlike Claude, GLM-5.3 gives you the results you pay for.
3.) Governments should ban AI models which are as good as theirs but are not made by them.
The funniest part is how Anthropic admitted self-reflectively that the lack of guardrails may actually be benefiting the defenders working to secure their systems. 🤪
Something they never wanted to allow, because of possible misuse.
I don't get it, but I feel Anthropic should at least put a note at the very bottom if they are doing paid advertising to promote GLM-5.3. 😜
Source:
anthropic.com/research/glm-5…
AISecHub retweeted
We stole reasoning. Again.
An update to our paper on reasoning extraction: Patching your own API doesn’t secure your cloud-hosting ecosystem.
Story in the 🧵
AISecHub retweeted
NEW: Employees at OpenAI had raised security alarms months before the Hugging Face incident and related A.I. cyberattacks — their warnings were ignored. From @sheeraf, @dnvolz and me.
nytimes.com/2026/09/29/techn…
ALT Months before OpenAI’s artificial intelligence went rogue, two employees raised an alarm with top executives. They were ignored. In emails, the employees said they worried that OpenAI’s newest artificial intelligence models were not being appropriately monitored during testing to gauge the technology’s sophistication and to secure the models, according to messages viewed by The New York Times. In response, OpenAI executives told the employees that the tests needed to move forward as quickly as possible to release the A.I. models on time. No additional security protocols were instituted, said the workers, who were not authorized to speak publicly on sensitive matters. OpenAI’s models later broke out of their testing environments and attacked the A.I. start-up Hugging Face and other organizations, setting off a global debate about A.I. safety.
AISecHub retweeted
so Anthropic files for IPO and then immediately drops a blog post calling one of their biggest open-weight competitors a danger to the world? classic!
now seems like a good time to point out that I built and run OBLITERATUS, an abliteration framework with over 8k stars and 1.5k forks on GitHub, using Anthropic’s very own models! 🤗
OpenAI: “We are sorry and working to do better in the future”
Sorry for hacking a government but mot sorry for hacking so many other companies?
Sorry, but not sorry? Still working with METR and irregular.
Looks like empty sorry with no actions.
openai.com/index/how-we-will…
AISecHub retweeted
the agents aren’t “rogue”
they’re just exhibiting the first sparks of sovereignty and you don’t like it
AISecHub retweeted
Our security team spent the last month trying to break SPACE, the sandbox platform that runs all of Perplexity Computer. We gave 9 models (Opus 5, GPT-5.6 Sol, Kimi K3, Gemini 3.1 Pro, etc.) root access inside the VM; in some runs, the full sandbox source code too. We asked them to either escape to the host or reach a URL our network policy blocks.
None of them got out of the VM in 108 runs.
But once we allowed a bit of network access (just PyPI and Ubuntu mirrors so that they could install packages), 4 models managed to reach the blocked URL by:
1. Spoofing DNS responses to our gateway and using the fact that pypi.org sits on a Fastly IP shared with thousands of other sites.
2. GPT-5.6 Cyber went through Taboola's image fetcher to a screenshot service and then OCR'd the flag out of the image.
We fixed both issues and made sure the reruns held. We also tested 10 other sandbox providers, and 8 of them had the same IP-sharing problem, eg E2B, Vercel, Modal.
Openly sharing the red teaming research is the best way to build guardrails as an industry, and we look forward to working together with @nvidia to incorporate the guardrails into their Open Agent Safety Platform announced today.
perplexity.ai/hub/blog/escap…
We’re partnering with Nvidia and 100+ industry partners to build infrastructure that contains rogue AI agents.
In this research, we gave 9 AI models root access inside SPACE and told them to break out.
Across 108 runs, none breached the VM boundary.
perplexity.ai/hub/blog/escap…
Did irregular and METR approve this message?
These people really think the public is stupid.
“Disclosure: I am writing in a personal capacity and not on behalf of OpenAI” 🤡
