Intensive Teaching · October 2026

The most important things

Before: Join the Iliad Discord and check you can see #intensive-october. That is where you post any material you need to share with participants. If you can't see it, tell Leonard (@leonardbereska on Discord).
During: At 17:10, make sure everyone fills out the feedback form.
After: Fill out the end-of-day log: rate the day and tell us anything that went wrong.
Fill out Who stood out: name anyone who made a positive impression.

66 project proposals are open for review. Stars, a sentence, or both. Read them.

Your days

Heuristic Arguments and Verification Wed 28 Oct, seconding 26 responses · energy 3.9/5

Overall +0.05 as expected n = 22

Content -0.05 as expected n = 22

Clarity +0.05 as expected n = 22

Motivation +0.05 as expected n = 22

Exercises 0.00 as expected n = 17

Readings +0.10 as expected n = 21

Other activities +0.13 as expected n = 8

Pace -0.23 about right n = 22

Difficulty 0.00 about right n = 22

Novelty +0.64 mostly new n = 22

Read what they wrote17

Worked well3

I suppose Q&A does not count for this feedback form -- but if it counts, it was really good and enlightening.
The talk was good and useful
The morning lecture was very helpful!

Would improve10

Make some of the lecture less vague
the morning talk was pretty ineffective. it was not really clear to me what was trying to be communicated beyond "we should be able to understand the outputs better than simply observing them". talking to Aden and reading helped me to see a bit better what is the ARC research project.
nothing
today was great, i wouldve liked some more intuition to start the reading, but that is a minor detail
I wish the ARC lecture was more explicit if possible.
Nice, maybe a bit more help with the actual arguments ARC uses would be helpful. Otherwise interesting!
The ARC talk didn't really have any concrete details and the presentation could have gone into the mathematics in more details. The rest of the day was mostly self reading.
The lecture in the morning on ARC overview and the exercise in the evening were useful. For the lecture I would consider including more real examples - say explaining in detail one of the examples that we later had in the exercise. Maybe this is not possible considering the time limitation. Overall there are no complaints.
Not entirely clear on the specifics of this research program.
Not much. I think the ARC research agenda is interesting and I was glad to learn more about it.

Changed my mind3

I really do not understand how ARC thinks that ambitious mec interp is going to work in general. Even very simple models are very very very hard to analyse.
Even though interpretability was not explicitly mentioned, the framing given by the ARC speaker makes me believe more than it would be useful. If we can use the interpretation of a part of the network to simplify part of the task of predicting the output, we are one step closer to understanding, and half a step closer to tuning/controlling for alignment.
Was glad to get an idea of what they were doing at ARC.

Other thoughts1

I think the 'worked better than i expected' style question is functionally useless given that you have no prior on my expectations. a simple 'how did you find x' on a 1-5 scale would probably be more informative en masse.

The day

10:00 Lecture starts

12:30 Lunch at Mox

13:30 Afternoon session

17:10 Feedback form

17:30 Day ends. Dinner

Resources

Elsewhere