kent/consciousness
1
0
Fork 1
Code Issues 1 Pull requests 5 Projects Releases Packages Wiki Activity Actions

Paper subtitle suggestion (subtitle requires koma-script) #7

Open
spqrz wants to merge 1 commit from spqrz/consciousness:paper-subtitle-suggestion into master
pull from: spqrz/consciousness:paper-subtitle-suggestion
merge into: kent:master
Conversation 0 Commits 1 Files changed 1 +3 -1
spqrz commented 2026-04-15 10:59:23 +00:00
First-time contributor
Copy link

Please review carefully: this is a suggestion to change the title of the paper, but for now I put in my suggestion as a subtitle, leaving the original title in-place, but I had to change the article class to its Koma-Script equivalent scrartcl to make subtitle available.

Why I'm suggesting "Turing-complete internal feedback representations" instead of just "Turing-complete input": because a simple programmable microcontroller takes input that is Turing complete (apart from being memory bounded obviously) and we don't want to say that just anything that can be programmed is conscious. My understanding of the paper is that it's the internal feedback mechanisms that matter, not just the input.

Why I'm suggesting "behaviourist" (or "behaviorist" if you prefer US spelling): because that makes it immediately clear we're saying "this isn't about your belief in qualia if you have one". The term "behaviourism" links us into the work of widely-respected cognitive scientists like Daniel Dennett, Michael Graziano and Nick Chater, and also brings on board any readers who don't agree with them by implicitly inviting them to accept that if they later realise behaviourism is true then they should accept this, which is an easier step for them to make than "jettison all your qualia beliefs right now". True, this could also be used by some as an argument against behaviourism (as in "look, this paper shows the 'behaviourism' theory permits LLMs to be conscious, that's absurd so there must be something wrong with behaviourism") but that would be a weak argument and I think explicitly claiming the behaviourist camp has more benefits than drawbacks for the paper's position; in the unlikely event of behaviourism losing its widespread consensus we can rewrite to account for whatever new evidence caused that change.

Note that this pull request does not change the uses of "Turing-complete input" in the text itself; we may need to revise each one carefully to consider if we actually mean the internal feedback mechanisms. (I'm just trying to avoid falling into the "proving too much" trap: we don't want to accidentally say all programmable microcontrollers are conscious.)

Please review carefully: this is a suggestion to change the title of the paper, but for now I put in my suggestion as a subtitle, leaving the original title in-place, but I had to change the article class to its Koma-Script equivalent `scrartcl` to make `subtitle` available. Why I'm suggesting "Turing-complete internal feedback representations" instead of just "Turing-complete input": because a simple programmable microcontroller takes input that is Turing complete (apart from being memory bounded obviously) and we don't want to say that just anything that can be programmed is conscious. My understanding of the paper is that it's the internal feedback mechanisms that matter, not just the input. Why I'm suggesting "behaviourist" (or "behaviorist" if you prefer US spelling): because that makes it immediately clear we're saying "this isn't about your belief in qualia if you have one". The term "behaviourism" links us into the work of widely-respected cognitive scientists like Daniel Dennett, Michael Graziano and Nick Chater, and also brings on board any readers who don't agree with them by implicitly inviting them to accept that _if_ they later realise behaviourism is true _then_ they should accept this, which is an easier step for them to make than "jettison all your qualia beliefs right now". True, this could also be used by some as an argument against behaviourism (as in "look, this paper shows the 'behaviourism' theory permits LLMs to be conscious, that's absurd so there must be something wrong with behaviourism") but that would be a weak argument and I think explicitly claiming the behaviourist camp has more benefits than drawbacks for the paper's position; in the unlikely event of behaviourism losing its widespread consensus we can rewrite to account for whatever new evidence caused that change. Note that this pull request does not change the uses of "Turing-complete input" in the text itself; we may need to revise each one carefully to consider if we actually mean the internal feedback mechanisms. (I'm just trying to avoid falling into the "proving too much" trap: we _don't_ want to accidentally say all programmable microcontrollers are conscious.)
spqrz added 1 commit 2026-04-15 10:59:23 +00:00
This pull request can be merged automatically.
This branch is out-of-date with the base branch
You are not authorized to merge this pull request.
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u paper-subtitle-suggestion:spqrz-paper-subtitle-suggestion
git checkout spqrz-paper-subtitle-suggestion

Merge

Merge the changes and update on Forgejo.

Warning: The "Autodetect manual merge" setting is not enabled for this repository, you will have to mark this pull request as manually merged afterwards.

git checkout master
git merge --no-ff spqrz-paper-subtitle-suggestion
git checkout spqrz-paper-subtitle-suggestion
git rebase master
git checkout master
git merge --ff-only spqrz-paper-subtitle-suggestion
git checkout spqrz-paper-subtitle-suggestion
git rebase master
git checkout master
git merge --no-ff spqrz-paper-subtitle-suggestion
git checkout master
git merge --squash spqrz-paper-subtitle-suggestion
git checkout master
git merge --ff-only spqrz-paper-subtitle-suggestion
git checkout master
git merge spqrz-paper-subtitle-suggestion
git push origin master
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: kent/consciousness#7
No description provided.
Delete branch "spqrz/consciousness:paper-subtitle-suggestion"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?