With one week left until the programme starts, we want you to start figuring out what you'd like to work on during the six days you'll be in Cambridge. Part of this is trying to understand your theory of change. What in the world do you want to affect, and how will you affect it?
For a six-day project your scope should be relatively tight. Having read some of the papers, you should have a sense of what kinds of experiments you'd like to try and the kinds of questions you want to research during your time. Be ambitious but mindful of the finiteness. Good luck!
How to use this unit2 readings + 1 video
Read both, watch the video, then write the sketch below.
OutputA one-page project sketch
Write it as you go. First version due Wednesday 12 August; final by Sunday 16 August.
READ 4.1Core20-25 min
You Need a Theory of Victory
Jason Hausenloy, The First Scattering (2026)
Jason Hausenloy separates a theory of change, your action X leads to good outcome Y, from a theory of victory, the full causal story of every step that has to go right, including the ones other people take. His tale of two verification teams is worth sitting with: one burns years on a VC-funded custom security chip, the other ships off-the-shelf hardware taps with its eye on what a US-China treaty would need.
Three mindsets for research on a clock. Truth-seeking (plausible results are usually wrong until you try to break them), prioritisation (a clear north star, checked daily), and moving fast (optimise for information gain per unit time, fail fast). Written for technical AI safety work, but broadly applicable.
Ideas and projects are heavy-tailed. The best project you pick can be far more impactful than your other options. Spending time picking between options is good, but timebox yourself to an hour or two of ideating. Favour projects that let you falsify beliefs quickly and run cheap experiments.
The board below covers Plan A's workstreams only, and the wider field is larger than this course. Aim for something you can scope to six days.
Plan A verification board
Where the inference-only retrofit stands
Plan A is one demanding use case for verification. It is a temporary training pause that still allows inference. Its proposed retrofit copies datacentre traffic, makes workloads reproducible, checks random samples by recomputation, protects the verifier, and closes routes for unverified outputs.
That system decomposes into 17 engineering workstreams. Each is marked by how much groundwork already exists, from active work you could build on to open problems you would start cold. This is not a ranking of importance.
Pick a row from the table to see where it stands. Most of these are bigger than six days, so if you take one on, choose a slice you could get a result on by Saturday. The five questions below help you scope it into a project.
01Claim
What must a lab, operator or state be able to claim?
02Evidence
What observable artifact could check the claim?
03Adversary
How could the evidence be evaded or tampered with?
04Test
What cheap result would change your view of feasibility?
05Handoff
Who uses the result, and what decision could it change?
4Active
At least one R&D effort exists, usually an early proof of concept. Replication, red-teaming and deployment work are still useful.
1Early testing
Early testing exists, but there is not enough evidence to judge the approach yet.
5Open
No active effort was identified, but the work is expected to be mainly tractable engineering.
7Open, hard
No active effort was identified and the problem looks research-hard. Scope down to a single assumption inside the gap.
Filter by status
01
Network evidence
Optical, network and datacentre systems
No workstreams match this status.
02
Reproducible workloads
ML runtimes, compilers and distributed systems
No workstreams match this status.
03
Partial recomputation
Algorithms, statistics and adversarial testing
No workstreams match this status.
04
Physical assurance
Trusted hardware, inspection and audit systems
No workstreams match this status.
05
Completeness
Memory, side channels and covert communication
No workstreams match this status.
Sketch your project
Adapted from the worksheet Aird uses in the video. Start from what you want to work on and follow it downstream; treat the questions as prompts, not things to answer precisely. Answers save as you type.
A rough sketch is fine, and nobody is grading it. Here is exactly what happens with it.
Submit below as soon as you have something, and by Wednesday 12 August at the latest.
On Thursday 13 August we post every sketch to the programme Slack. Read the others before you arrive to see who is thinking about similar things.
You can revise and resubmit here until Sunday 16 August. We work from your latest version.
On the first day we use the sketches to settle projects and match you with residents. Do not polish.
If you want feedback sooner, copy your sketch with the button below and send it to another participant.
