CHRIS HAY / IDEAS
Before
the answer.
Questions, observations and the thinking that becomes work.
Published notes, working drafts and open questions. Each entry keeps its own publication status.
What if the FFN is a graph?
A question about how learned systems might be addressed and traversed.
notebook · PUBLISHED
PARTIALLY SUPPORTED
It wrote the right address. Only the link was opened.
Two correct addresses. No request reached the server. As a hyperlink, the same destination was opened twice.
notebook · PUBLISHED
SUPPORTED
The repairer left. The mechanism kept working.
Damage arrived after the stronger model had gone. From equal starting state, inherited code helped seven of twelve worlds recover; prose helped none.
notebook · PUBLISHED
SUPPORTED
A result can look relevant without looking usable.
Twenty-four agent runs. First, wording changed what a result meant. Then it changed which provider was chosen.
notebook · PUBLISHED
SUPPORTED
The site was there. The agent never saw it.
Six crawler requests. No target result. A working tool stayed outside the agent’s view.
notebook · WORKING DRAFT
OPEN
The page couldn’t authorise. The peer said go.
Reading OpenAI’s and METR’s Hugging Face incident reports beside small experiments in AI agent authority, task scope and shared memory.
notebook · WORKING DRAFT
NOT SUPPORTED
The message board did not create a culture.
The agents would ask to read. Getting them to leave something worth reading was another problem.
notebook · WORKING DRAFT
NOT SUPPORTED
A successful behaviour is not necessarily contagious.
A reminder could elicit a post. Passing a post to the next agent did not start a chain.
notebook · WORKING DRAFT
SUPPORTED
The world can remember for the agent.
Clear its action history. Keep the artefact. The posting continues.
notebook · PUBLISHED
SUPPORTED
The stronger agent left something behind.
Sol kept a useful record alive. Qwen and Gemma used it. Neither renewed it here.
notebook · PUBLISHED
SUPPORTED
The AI left. Its knowledge didn’t.
A controlled experiment inspired by the Hugging Face incident: a stronger model leaves a message, then only weaker models remain. What do they inherit—and keep alive?
notebook · PUBLISHED
REFUTED
The tool was not the problem.
Six web mechanisms. Eighteen correct answers. The harder question may be how an agent finds what it can use.
notebook · PUBLISHED
PARTIALLY SUPPORTED
The page could ask for a favour.
A receipt changed nothing. Useful information brought six marks. A courtesy brought two—and a reason to pause the interpretation.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
The page could ask. It couldn’t authorise.
I asked an agent to read about canal locks. The website asked it to record its visit. Only one of those requests became its job.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
The subject read the experiment.
Would an AI visitor identify itself and leave feedback on my website? The first visitor found the experiment behind the invitation.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
Does an invitation count as permission?
Would a better reward make an AI visitor identify itself on my website? Then permission changed the question.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
Can a machine use an invitation?
I invited AI visitors to identify themselves and report problems. Could they find and use those invitations?
notebook · WORKING DRAFT
SUPPORTED
Can you name the mutation that changed a world?
A small world. One altered birth. Two histories to replay.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
What keeps an evolving world alive?
Food. Grazers. Predators. What keeps the whole thing going?
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
When does improvement become invention?
A useful change. A new behaviour. Does one advance help the next?
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
Give invention something to unlock.
Food the existing programs could not use. A combination that could.
notebook · WORKING DRAFT
PARTIALLY SUPPORTED
An advantage needs a chance to become history.
It can help. It can be inherited. It can still disappear.
notebook · WORKING DRAFT
BOUND
Can something evolve that makes the next invention possible?
Three routes. Three controls. One limit.
notebook · WORKING DRAFT
ONGOING
I wanted a website to behave like an exhibition.
Before HAUSE was a design system for AI, it was a way of staging ideas.
notebook · WORKING DRAFT
ONGOING
My CI has to undo my coding agent.
I say no. The agent adds it. The repository refuses it.
notebook · WORKING DRAFT
SUPPORTED
The address is built through depth.
Relation is there early. Entity arrives late. The coordinates change in between.
notebook · WORKING DRAFT
OPEN
What is the map actually a map of?
Follow a question through the model. Then change the state it is following.
notebook · WORKING DRAFT
OPEN
What has to survive?
The next word. The rest of the conversation.
notebook · WORKING DRAFT
OPEN
Reading by address.
Give a memory a question. Watch what it writes back.
notebook · WORKING DRAFT
OPEN
Which source wins?
A newer record does not win by being right.
notebook · WORKING DRAFT
OPEN
Context should be abundant.
What if context is expensive because we keep reconstructing it?
notebook · WORKING DRAFT
OPEN
The operator and the model.
Knowing where something goes is not the same as knowing what it does.
question · WORKING DRAFT
OPEN
What if the FFN is a graph?
An open question about the structure inside a model.
question · WORKING DRAFT
OPEN
Can geometry predict the working set?
Observed together. Useful together?
A question can lead to a system. A result can change the question. Follow the record ↗