ML Safety Newsletter
Dan Hendrycks, Alice BlairML Safety Research News
| Platform |  | Pricing | Only free issues | Publishes | Infrequently |
|---|---|---|---|---|---|
| Issues | 18 | Founded | 5 years ago | Last Issue | 4 months ago |
| Active | |||||
Read this Newsletter
newsletter.mlsafety.orgLatest Issues
MLSN #18: Adversarial Diffusion, Activation Oracles, Weird Generalization
Diffusion LLMs for Adversarial Attack Generation
TLDR: New research indicates that an emerging type of LLM, called diffusion LLMs, are more effective than traditional autoregressive LLMs for automatically generating jailbreaks.
Thanks f...
MLSN #17: Measuring General AI Abilities and Mitigating Deception
Measuring General AI Abilities
TLDR: New metrics say that frontier AIs get 57% on tests for general intelligence and are able to do 2.5% of remote freelance-type work.
Many benchmarks measure AIs on useful knowledge and abilities, but t...
ML Safety Newsletter #16
Prophet Arena
TLDR: Frontier LLMs can forecast world events with accuracy similar to prediction markets.
UChicago SIGMA lab and Kalshi released a benchmark called Prophet Arena, measuring AI agents’ ability to forecast world events. The...
ML Safety Newsletter #15
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
Researchers from EPFL and CMU have developed OS-Harm, a benchmark designed to measure a wide variety of harms that can come from AI agent systems. These harms can take thre...
ML Safety Newsletter #14
Defeating Prompt Injections by Design
Researchers at Google DeepMind pioneered a new system called CaMeL for preventing prompt injection in AI agents—attacks where an AI agent encounters malicious instructions in the course of executing...
Audience Metrics
Subscribers, engagement, traffic and sponsorship for ML Safety Newsletter.
| Subscribers | Engagement | 65 | Monthly Web Visits | ||
|---|---|---|---|---|---|
| Accepts Sponsors | Estimated Cost per Ad | ||||
Explore More
Authors
The writers behind this newsletter.
Director of the Center for AI Safety (safe.ai)
Writing about the future of AI safety and security. About me: https://www.aliceblair.net/
Social
Frequently Asked Questions
How can I access the email archive for ML Safety Newsletter?
You can find recent issues that have been published by ML Safety Newsletter 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 ML Safety Newsletter have?
To see how many people subscribe to ML Safety Newsletter, 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 ML Safety Newsletter?
Newsletter advertising can be extremely effective when it's done right. Before you pitch ML Safety Newsletter 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 ML Safety Newsletter?
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 ML Safety Newsletter using the contact information provided and ask for a copy of their media kit.
How can I find newsletters related to ML Safety Newsletter?
Scroll up to where it says Related Newsletters to see other publications like ML Safety Newsletter. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
How do I contact ML Safety Newsletter?
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.