AI Safety and Alignment Group
Maksym Andriushchenko, Luca Beurer-Kellner, Hardik Bhatnagar, Sahar Abdelnabi, Dongyang Fan, David, Ben RankAI Safety and Alignment Group at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems
| Platform |  | Pricing | Only free issues | Publishes | Weekly |
|---|---|---|---|---|---|
| Issues | 6 | Founded | 7 months ago | Last Issue | 2 months ago |
| Active | |||||
Read this Newsletter
aisagroup.substack.comLatest Issues
How does persistent memory affect AI safety?
Memory Is Coming
Persistent memory is a central missing piece for long-horizon task execution, digital co-workers, and lifelong agents. Persistent memory would allow AI to do autonomous work over long time-horizons and to improve from e...
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
If you’ve used Claude Code, Gemini CLI, or OpenAI’s Codex CLI recently, you’ve probably noticed how much more capable coding agents have become. And a big part of that is the emerging ecosystem of “agent skills,” third-party instruction pac...
HalluHard: A Hard Multi-Turn Hallucination Benchmark
Model rankings on HalluHard. Lower values are better.
A lot of hallucination evaluation assumes a single turn: ask a question, check the answer. But real use looks like multi-turn back-and-forth, where context grows, earlier mistakes get...
PostTrainBench: Measuring AI Ability to Perform LLM Post-Training
TLDR:
-
PostTrainBench is our new benchmark that measures whether AI agents can successfully post-train language models—a key capability for AI R&D automation.
-
Each agent is based on a frontier LLM and a native CLI agent scaffold. F...
Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
TLDR:
-
Agent Skills is a feature that loads instructions from markdown files to give agents task-specific abilities.
-
Every line in these skill files is an instruction, which makes prompt injections trivial.
-
We show realistic...
Key Facts
Audience Metrics
Subscribers, engagement, traffic and sponsorship for AI Safety and Alignment Group.
| Subscribers | Engagement | 71 | Monthly Web Visits | ||
|---|---|---|---|---|---|
| Accepts Sponsors | Estimated Cost per Ad | ||||
Explore More
Authors
The writers behind this newsletter.
I am a principal investigator at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems. I also serve as chapter lead for the new edition of the International AI Safety Report chaired by Yoshua Bengio.
Working on secure agentic AI @snyksec. Previously: PhD @the_sri_lab, ETH Zürich. CTO@Invariant Labs. LMQL author
Evals, Long horizon, Interp, Safety
I am a Principal Investigator at the ELLIS Institute Tübingen where I lead the COMPASS research group focusing on AI safety, security, human aspects, and multi agent systems.
PhD student at EPFL
PhD Student in AI Safety and Alignment
PhD student working on AI safety.
Frequently Asked Questions
How can I access the email archive for AI Safety and Alignment Group?
You can find recent issues that have been published by AI Safety and Alignment Group on Reletter by scrolling up to where it says Latest Issues. Tap on the link for any of the most recent emails or hit More Issues to see older ones.
How many subscribers does AI Safety and Alignment Group have?
To see how many people subscribe to AI Safety and Alignment Group, simply upgrade your Reletter account. We provide readership numbers and lots of other stats for this newsletter so you can decide if it's worth reaching out to.
How can I advertise in AI Safety and Alignment Group?
Newsletter advertising can be extremely effective when it's done right. Before you pitch AI Safety and Alignment Group as a potential sponsor or partner, make sure that you've done your research and checked its newsletter stats with Reletter.
Then, personalize one of our winning pitching templates and send it to the right person using the contact info provided.
How much does it cost to sponsor a publication like AI Safety and Alignment Group?
Newsletter ad rates (or CPM) vary depending on many factors, including industry, number of subscribers, open rate, ad placement and more.
To find out how much an ad will cost, contact AI Safety and Alignment Group using the contact information provided and ask for a copy of their media kit.
How can I find newsletters related to AI Safety and Alignment Group?
Scroll up to where it says Related Newsletters to see other publications like AI Safety and Alignment Group. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
How do I contact AI Safety and Alignment Group?
Reletter provides this newsletter's website URL above, where you will often find their contact information. We also provide links to associated social media accounts and pitching templates so you can reach out fast.