AI Safety Research on Pessimistic Agents (Long Term Future Fund grant recipient).

Doing part-time work with Cambridge Effective Altruism, leading local AI Safety field building efforts and helping to coordinate pipelines globally.



Sorted by New

Wiki Contributions


What Are Your Software Needs?

A scheduling service that works across multiple timezones.

Specifically for organising seminar series with 100s of participants and 10s of facilitators. We need to:

  • Take in facilitator & participants' availabilities, submitted by them in their timezone
  • See, for each participant, which facilitators are available at this time. (So that we can match appropriate facilitators to the knowledge status of each participant, constrained on availability.)
  • Preferably some adjustment for upcoming daylight savings, but that's a stretch.

Current solutions: when2meet doesn't sync across timezones for Mon-Sun availabilty (only specific dates). Lettucemeet has weird overflow errors around midnight, and does not work in India (+4.5 hours, I believe).

This problem is known to some people, and I don't know the status of solving it at time of writing the comment (I expect the work has not been started though). Do get in touch if you're interested in this problem before going ahead with anything, all the same!

What is most confusing to you about AI stuff?

Here are some big and common questions I've received from early-stage AI Safety focused people, with at least some knowledge of EA.

They probably don't spend most of their time thinking about AIS, but it is their cause area of focus. Unsure if that meets the criteria you're looking for, exactly.

  1. What evidence would be needed for EA to depriotise AI Safety as a cause area, at least relative to other x-risks?
  2. What is the most impactful direction of research within AIS (common amongst people looking for their first project/opportunity. I usually point them at this lesswrong series, as a starting point).
Women's Empowerment: Founders Pledge report and recommendations

Hi - am a little late to your comment, but unsure that the other replies address this. Though 80% of homicide victims are male, this doesn't mean anything like 80% of men experience homicide. However 35% of women experience intimate partner violence or sexual violence. It seems to me like the homicide statistic you give doesn't take the scale of homicide into account, which is much smaller than 35% of the male population. I would accept your point that the comparable rate for intimate partner violence of any kind for men isn't given, which while my prior is that this is lower isn't easily evidenced as you point out.