I am still watching the recordings of talks given on the #39C3 Chaos Communications Congress (see the talks here). Katharina Nocun gave a talk titled Doomsday-Porn, Schäferhunde und die „niedliche Abschiebung“ von nebenan where she shows a really disturbing trend: AI-generated content is becoming a cornerstone of authoritarian and far-right communication strategies.
(more…)Tag: AI
-
The Malicious (Coding) Agent …
I just watched Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents from Johann Rehberger on the #39c3. He shows quite impressive how the future threat model looks like, the more AI Agents are deployed.
In his talk he demoes a couple of attacks that were applied by using agents. I don’t want to summarize the talk here (you might want to read the heise online article instead), but it is ways beyond “simple prompt injection”!
But my most “aha”-moment was the statement to treat an Agent as a Malicous Internal. Which is probably the worst scenario you want to deal with. Usually you would like to trust your co-workers and not treat them as if they could stab you in the back while smilig at you.
Anyways, I’m pretty sure the technology will evolve into more secure ways. But it will also stay as a new way of attack in the future. I’d recommend checking it out!
https://media.ccc.de/v/39c3-agentic-probllms-exploiting-ai-computer-use-and-coding-agents
PS: I’d embed it here, but this obviously requires some CSS / WordPressTheme-magic …
Related links:
- 39C3: Power Cycles – media.ccc.de (all videos)
Fediverse Reactions
-
How to write great agents.md(s) – A recommendation from GitHub
GitHub’s new guide, How to write a great agents.md: Lessons from over 2,500 repositories, pulls lessons from over 2,500 repositories to show how to document AI agents effectively. It’s not just about clarity but also about making collaboration, reproducibility, and scalability possible.
The guide breaks down how to structure
agents.mdfiles for real-world utility. It highlights common mistakes and explains why solid documentation is the backbone of any successful AI project. Whether you’re a developer, DevOps engineer, or just curious about AI tooling, this is a practical roadmap.For anyone serious about AI development, this is a resource worth keeping: https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
-
LLM Update in Production: When Prompts Fail — and What It Means for Your Applications
t3n recently wrote that OpenAI’s GPT 5.1 update might come with a surprise to desktop users: previously reliable prompts no longer behave as expected. While this may be just a minor annoyance in day-to-day chat interactions, think about what that means in production environments.
(more…) -
I break things … Google Veo
Recently I had the opportunity to test the new Google AI-Video generator powered by Veo 3(.1). The demo was truley impressive and scary at the same time! And then we were able to test it ourselves …
(more…) -
o365 “control plane” for AI Agents coming
I just read an article on InfoWorld, that Microsoft rolls out Agent 365 ‘control plane’ for AI agents. The description sounds quite well what an enterprise needs in terms of compliance and security:
Microsoft said that Agent 365 unlocks five capabilities intended to make enterprise-scale AI possible:
- Registry, to view all agents in an organization, including agents with agent ID, agents registered by the user, and shadow agents.
- Access control, to bring agents under management and limit access only to needed resources.
- Visualization, to explore connections between agents, people, and data, and monitor agent performance.
- Interoperability, by equipping agents with applications and data to simplify human-agent workflows. They would be connected to Work IQ to provide context of work to onboard into business processes.
- Security, to protect agents from threats and vulnerabilities and remediate attacks that target agents.
-
What I am Missing in Most GenAI Conversations
When people talk about Generative AI, the focus is usually on:
- Prompting
- LLMs
- Chatbots
- Proofs of Concept (POCs)
But what I am missing a lot in those conversations are:
- Try classic automation first
- Process integration: Can I add it into a process so that it fixes a problem?
- Data privacy
- Security
- Works council/employee representation (if applicable)
- Observability (not just the usual observability but also prompts and responses)
- Robust data pipelines (a.k.a ETL)
- Model Selection
- Model decay & re-evaluation (How often will you need to update? Currently about ~1x / year)
- Regulatory Compliance AI Act (EU)
- Costs (Tokens, maintenance, scaling — over years, not demo days)
- Scalability
- Latency & Performance:
- Testing (“it works in demo” ≠ “it works in production with real users”)
- Human-in-the-Loop (HITL):
- The other 95% of the app (The “boring” software stack around the AI)
- APIs (If it’s meant to automate, it needs to talk to other systems)
If there’s a user interface:
- Interface design & UX (no one uses what they can’t understand)
And the elephant in the room:
- How do you address the fear—justified or not—that you might be innovating people out of their jobs?
Fediverse Reactions
-
Why Your Favorite AI Tool Might Be Isolating You
AI chat tools are a remarkable invention. Their rapid adoption speaks for itself: instant access to information, tailored feedback, and the ability to explore ideas or discuss one own thoughts or questions without friction – never before did we have such opportunities. But this power can come with a risk.
(more…) -
Github Copilot is the Coach I always Wanted
We hear a lot about the bad side of AI Code Generation etc. But there are also quite some good sides that should not be ignored.
(more…)
