We study intelligent behavior across a broad range of contexts to build the foundational understanding required to create aligned AI systems. Formerly PIBBSS.
We’re hiring Research Scientists in Ambitious Mechanistic Interpretability to study how the features AI systems learn are rooted in data.
Remote, full-time, from January 2027. $125,000–$170,000 a year, by seniority and location.
Apply by November 20: princint.ai/research-scienti…#AISafety#AISJobs
🚨 Applications for Research Scientists on Ambitious Mechanistic Interpretability close in two days!
Interested? Check out the job description here: princint.ai/research-scienti…#AISafety#AISJobs
The Alignment Journal is looking for reviewers for "Ecology of Self-Replicating AI Agents: Collaboration Creates a Population Threshold for Takeoff".
You might be interested if you have experience with population dynamics, AI cyber capability or self-replication evals, multi-agent scaling, or malware and botnet spread models.
Authors stay anonymous while the paper is under review. Reviewers are paid, with a bonus for being early. Nominate yourself ⬇️
Now under review at the Alignment Journal: “General Agents Contain World Models, even under Partial Observability and Stochasticity”.
Reviewers for this paper have been found.
To review in the future, make an account on our website and list your expertise. Editors will search among the accounts when recruiting reviewers for new papers. You can also nominate yourself.
Some chain-of-thought models write down that they will deceive the user. Newer models increasingly reason without writing anything down.
@FirstPrincip1es reports on how @PrincInt’s Horizon Scanning team is turning to physics to look inside them.
👉 Read the article here:
firstprinciples.com/blog-art…
🚨 Deadline extended: Applications for the Horizon Scanner role in our new Coordinated Research Programs now close on 4 December.
The role is a paid ~four-month remote contract ($25,000–$38,000), with a path to Technical Director of the program you help scope.
👉 Learn more here: princint.ai/now-hiring-horiz…#AISafety#AISJobs
🚨 Applications for the Horizon Scanner role in our new Coordinated Research Programs close tomorrow, 5 November.
If you map open problems and bring the right people to them, we’d like to hear from you.
Learn more at princint.ai/now-hiring-horiz…#AISafety#AISJobs
The Alignment Journal publishes research on the scientific foundations of understanding, predicting, and steering artificial intelligent systems. As of today, submissions are open to everyone.
What we do differently:
- We pay reviewers, with bonuses for speed and insight.
- Review discussion is confidential, but every accepted paper is published with a “review summary” to distill the insights generated.
- Each paper is judged against our acceptance bar, not against other submissions.
- Papers under review are listed publicly, and researchers can nominate themselves to review, so each paper can reach the reviewers who know the topic best.
We seek work that builds theoretical or otherwise principled analyses of agency, robustness, incentives, interpretability, generalization, and long-term behavior, and whose significance survives the deletion of any particular model, dataset or benchmark. Empirical investigations of such ideas are welcome, and negative results are encouraged.
We are especially interested in approaches that could apply to future superintelligent systems that interact and self-improve.
You can submit your preprint in any format. Submissions are rolling and open now on the website.
If you are instead interested in reviewing or serving as an action editor (basically: an area chair), create an account on our website.
Links to submit, our scope and the reasoning behind the Journal are in the reply ⬇️
We are thrilled to be a community partner of Vision Weekend USA, taking place in San Francisco from 13 to 15 November, as @foresightinst celebrates its 40th year 🎉
We invite you to check out the lineup, featuring over 30 speakers across secure AI, neurotechnology, biotech, and space.
👉 Event page & tickets: foresight.org/events/vision-…
We’re #hiring a Senior Compliance & Legal Operations Manager to own compliance across @PrincInt’s US and UK charities and sponsored #AIsafety projects.
Remote, full-time, starting 15 November. Salary benchmarked by location.
Apply by 30 October: princint.ai/now-hiring-senio…
We’re hiring Horizon Scanners for four new Coordinated Research Programs in #AISafety. Paid four-month remote contract, with a possible path to Technical Director.
If you map open problems and bring the right people to them, we’d like to hear from you.
Apply by November 5, 2026: princint.ai/now-hiring-horiz…