Unsupervised Learning 2.0: A Day of Research Discussions

November 20, 2025

Event Overview

Unsupervised
Learning

We're hosting Unsupervised Learning again — a day to explore important recent developments in frontier AI safety. (You will be doing the unsupervised learning, not the models!)

​Everything is optional, so drop in and out of sessions as you find useful. We’ll also have plenty of time for 1:1 meetings between people working on similar projects, and space to catch up on work and relax.

​This event is for researchers from frontier AI companies and some independent research orgs, but it's invite-only, so please check with us before sharing. 

​​Register here by Friday, November 14 EOD if you haven’t already. Last minute attendees contact isaac@constellation.org

Event Details

  • Date
  • November 20, 2025
  • Location
  • Constellation Research Center
    2150 Shattuck Ave, Berkeley, CA
  • Format
  • Lightning talks, research discussions, Q&As, 1:1s, co-working, lunch and dinner – everything optional!
  • Refreshments
  • Breakfast, lunch, dinner, and all day snacks provided

Additional location information:

Sessions will be hosted in Constellation’s workspace in Downtown Berkeley. Food, drinks, and workspace amenities (workstations, call booths, meeting rooms) available to all attendees. The space will be open from 8:30am until late for co-working and conversations between sessions. Specialized workspace needs are available upon request. (Contact Henry, henry@constellation.org.)

Schedule

Feel free to use any coworking rooms, meeting rooms, common spaces, and phone booths. Do any activities that fit your schedule.

9:00 AM

Doors open for coworking and 1:1s

11th Floor

9:30 AM

Breakfast: Boichik bagels, Signal coffee, and Elaichi chai!

11th Floor

11:30 AM - 12:30 PM

Lightning talks on the future of misalignment

Lunch Area

Quick-fire presentations from researchers across participating organizations

  • Wojciech Zaremba, OpenAI
  • Buck Shlegeris, Redwood Research
  • Alex Turner, Google DeepMind
  • Owain Evans, Truthful AI

12:30 PM

Lunch

Lunch Area

1:30 PM - 2:00 PM

Reward hacking in production RL environments can induce broad misalignment

Breakout Room 1

  • Evan Hubinger, Anthropic

Stress testing deliberative alignment for anti-scheming

Breakout Room 2

Quick-fire presentations from researchers across participating organizations

  • Jenny Nitishinskaya, OpenAI

2:00 PM - 2:30 PM

Break

2:30 PM - 3:00 PM

Topic TBA

Breakout Room 1

  • John Schulman, Thinking Machines

Extrapolating METR's agent time horizon graph

Breakout Room 2

  • Nikola Jurković, METR

Believe it or not: how deeply do LLMs believe implanted facts?

Breakout Room 3

  • Stewart Slocum, xAI (work done at Anthropic)

3:30 PM - 3:30 PM

Break

3:30 PM - 4:00 PM

Topic TBA

Breakout Room 1

  • John Schulman, Thinking Machines

Instructing models to misbehave at train-time can improve run-time behavior

Breakout Room 2

  • Sam Marks, Anthropic

Training away spurious side-goals with regularized RL

Breakout Room 3

  • Jacob Pfau, UK AISI

4:00 PM - 4:30 PM

Break

4:30 PM - 5:15 PM

A mainline plan for mitigating misalignment risk

Breakout Room 1

  • Ryan Greenblatt, Redwood Research

What should the spec be for very capable models?

Breakout Room 2

  • Jason Wolfe, OpenAI

5:15 PM - 6:00 PM

Break

6:00 PM

Breakout Space

Dinner

Lunch area

You're welcome to stay as long as you like for dinner and more conversations.

Logistical Information

Where

​Sessions will be hosted in Constellation’s workspace in Downtown Berkeley. Meals, snacks, and workspace amenities (workstations, call booths, meeting rooms) available to all attendees.

​The space will be open from 9:00 until late for conversations and co-working between sessions. Specialized workspace needs are available upon request (contact Isaac, isaac@constellation.org).

Flexible Attendance Options

  • Mix and Match: Do any activities that fit your schedule.
  • Full Day Experience: Join us for informal conversations, coworking, 1:1s, and optional scheduling (lightning talks, deep-dive sessions, and happy hour.

Who Should Attend

We welcome anyone excited to engage with others working on cutting edge AI Safety and frontier models. We welcome thoughtful critics and different intellectual perspectives. Your questions and challenges help shape productive discussions and encourage ongoing dialogue.

What is Constellation? 

​We are an independent, nonprofit research center hosting over 200 individual researchers and organizations working on frontier problems in AI safety. You'll connect with many of our affiliates throughout the event, both as speakers and fellow attendees.

​Interested in working from Constellation for a day? Just let isaac@constellation.org know the date you’ll be coming!

Arrival & Parking

Our address is 2150 Shattuck Ave, Berkeley, CA. We are in the Chase Building right by the Downtown Berkeley BART. The entrance is off Shattuck Ave. Buzz yourself up from the lobby to floor 11. We will greet you! Call 1-510-200-8195 with any questions (don’t text). 

Park in Downtown Berkeley. We recommend parking in Allston Way Garage (2061 Allson Way, Berkeley, CA, 94704.) You can enter from Allston Way or Center Street. After entering the lot, you can get free parking by using the code “Constellation” with AirGarage. More parking info is here.

Accessibility & Accommodations

We are committed to making this event accessible to all participants. Please contact us regarding accessibility accommodations, unusual dietary restrictions and food allergies, or any other needs to ensure your participation. All our meals cater for people with common allergies or restrictions by default.

Code of Conduct

Everyone is expected to be considerate, professional, and collaborative. We also expect people to follow the rules of their organizations. Here is our full Code of Conduct.

Confidentiality

There is no specific confidentiality policy. Respect the intentions of the people you speak to, as normal – check in before you share something widely if it seemed to be shared in a more confidential context.

Photography

  • No photography.
  • Please respect presenter preferences regarding recording or sharing of specific content.

Contact Information

For questions, accommodation requests, or additional information: