Musings on the Alignment Problem
Jan Leike| Platform |  | Pricing | Only free issues | Publishes | Infrequently |
|---|---|---|---|---|---|
| Issues | 14 | Founded | 5 years ago | Last Issue | 4 months ago |
| Active | |||||
Read this Newsletter
aligned.substack.comLatest Issues
Alignment is not solved
I’ve been optimistic about alignment for a while now, but when I first wrote about this in 2022, there was a lot more uncertainty about how the technology would develop. Since then a lot has happened: pretraining continued improving and RL...
Should we control AI instead of aligning it?
The basic pitch for AI control is to build systems around capable models that ensure they can’t cause harm even if they were misaligned. For example, a misaligned model could deliberately introduce subtle mistakes or bugs or try to go rogue...
Crisp and fuzzy tasks
This is a taxonomy for task space that I find useful when thinking about what we need to do to solve alignment.
- Crisp tasks are more reasoning/system-2 based. Whether a response is good is typically precisely defined. Reasonable, knowl...
Two alignment threat models
Misalignments in models typically fall somewhere between the two ends of this spectrum:
- Under-elicited models: The model doesn’t try as hard as possible on the task, so its performance is worse than it could be if it was more aligned....
Combining weak-to-strong generalization with scalable oversight
The idea behind our latest paper on weak-to-strong generalization (W2SG) is that we finetune a large pretrained model to generalize well from supervision that is weaker (less accurate) than this large model. In the paper we use weak supervi...
Key Facts
Audience Metrics
Subscribers, engagement, traffic and sponsorship for Musings on the Alignment Problem.
| Subscribers | Monthly Web Visits | Accepts Sponsors | |||
|---|---|---|---|---|---|
| Estimated Cost per Ad | |||||
Explore More
Authors
The writers behind this newsletter.
Frequently Asked Questions
How can I access the email archive for Musings on the Alignment Problem?
You can find recent issues that have been published by Musings on the Alignment Problem 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 Musings on the Alignment Problem have?
To see how many people subscribe to Musings on the Alignment Problem, 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 Musings on the Alignment Problem?
Newsletter advertising can be extremely effective when it's done right. Before you pitch Musings on the Alignment Problem 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 Musings on the Alignment Problem?
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 Musings on the Alignment Problem using the contact information provided and ask for a copy of their media kit.
How can I find newsletters related to Musings on the Alignment Problem?
Scroll up to where it says Related Newsletters to see other publications like Musings on the Alignment Problem. You can also search our email newsletter directory to discover other newsletters that cover the topics you're interested in.
How do I contact Musings on the Alignment Problem?
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.