
We research catastrophic AI risks and techniques that could be used to mitigate them.
| Platform | Pricing | Only free issues | Publishes | Daily | |
|---|---|---|---|---|---|
| Issues | 135 | Founded | 3 years ago | Last Issue | 3 days ago |
| Active | |||||

Many control protocols work by intervening on an untrusted AI’s actions during deployment. For example, you might set up a monitor that scores each action’s suspiciousness and blocks actions above a threshold, replacing them with actions fr...
Summary: Currently, “chain of thought” (CoT) is our most valuable tool for understanding the reasoning and cognition of AI systems. However, some architectures would enable AI models to reason much more extensively in latent states rather t...
We measure GPT-6-Astra’s capabilities when its prompt is padded with a variable number of meaningless “filler” tokens (e.g., dots) and it is told to answer immediately1 without reasoning. On tasks designed to require lots of serial cognitio...
The CoTControl eval asks reasoning models to follow formatting constraints in their chain-of-thought (e.g. write in all lowercase, avoid a specific word) while solving questions. Models seem to mostly be pretty bad at this: recent models sc...
Currently, chain-of-thought (CoT) is a valuable tool for overseeing AI models. However, some architectural shifts could significantly reduce CoT monitorability. We have recently proposed that AI companies should transparently share inform...
Subscribers, engagement, traffic and sponsorship for Redwood Research blog.
| Subscribers | Engagement | 80 | Monthly Web Visits | ||
|---|---|---|---|---|---|
| Accepts Sponsors | Estimated Cost per Ad | ||||
Where Redwood Research blog ranks on Google, and how much search traffic it brings in.
| Ranked Keywords | 133 | Monthly Search Traffic | Top Keywords |
|---|
The writers behind this newsletter.
Redwood Research
I work at Redwood Research on technical AI security+safety research.
Helping navigate transformative AI
Researching AI safety, sometimes writing fiction
“every conceivable… objection, including those that would occur only to the malicious or the clinically literal-minded” | math & philosophy at magdalen
Research Analyst at Redwood Research.
Working on AI Safety
You can find recent issues that have been published by Redwood Research blog 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.
To see how many people subscribe to Redwood Research blog, 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.
Newsletter advertising can be extremely effective when it's done right. Before you pitch Redwood Research blog 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.
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 Redwood Research blog using the contact information provided and ask for a copy of their media kit.
Scroll up to where it says Related Newsletters to see other publications like Redwood Research blog. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
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.