I'm NOT confused about 'how could AIs send each other a link to their Git repo?'. I'm confused as to what other info would convince an AI that any particular source code is what another AI is running. How could any running system prove to another what source code it's running now? How could a system prove to another what source code it will be running in the future?
I'm NOT confused about 'how could AIs send each other a link to their Git repo?'. I'm confused as to what other info would convince an AI that any particular source code is what another AI is running. How could any running system prove to another what source code it's...
The post: * siderea | Improper Nouns [p/a/s, Patreon] Interestingly, 'improper nouns' – as described by the post – is itself an example of the phenomena it describes (as 'improper noun' is itself an existing term): > There's a thing you probably have encountered and maybe haven't really registered as...
Matthew Cook probably violated an NDA he signed with Wolfram Research This is a follow-up to this comment on a previous post of mine about (Stephen) Wolfram. The comment, by gwern: > > Charitably, I think that makes his apparent 'arrogance' better understood as something like a 'literary convention', especially...
On the paradox of tolerance in relation to fascism and online content moderation – Unstable Ontology I found the post to be wonderful. It expresses my own thoughts and feelings extremely well. Some comments I made on the ACX post that shared this: > YESSSSS! Tolerate all speech! Persecute the...
Background: * Bounded Distrust - by Scott Alexander - Astral Codex Ten I'm curious about both: * Generalities – for all/most/some governments (and different types of hearings if that's relevant) * Specifics – (relatively) concrete details about specific governments, or specific hearings My own model (roughly): 1. Hearings are, by...
I think this might be the 'best' 'free solo' free solo video (including "Free Solo" the movie, or any other climbing movie I've seen): * I tried free solo with Alex Honnold Insane experience - YouTube I was pretty disappointed by "Free Solo" – not much climbing! (Watch "The Dawn...
Link: * The madness of reduced medical diagnostics This is (or seems to me now to be) an obvious-in-hindsight and I'm sad that I've never (or don't remember having) encountered it; at least not so succinctly. I'd like to try putting this 'advice' into practice myself, e.g. demanding doctors share...
Was this not originally tagged “personal blog”?
I’m not sure what the consensus is on how to vote on these posts, but I’m sad that this post’s poor reception might be why its author deactivated their account.
I just reported this to Feedly.
Thanks for the info! And no worries about the (very) late response – I like that people fairly often reply at all (beyond same-day or within a few days) on this site; makes the discussions feel more 'timeless' to me.
The second "question" wasn't a question, but it was due to not knowing that Conservative Judaism is distinct from Orthodox Judaism. (Sadly, capitalization is only relatively weak evidence of 'proper-nounitude'.)
Some of my own intuitions about this:
I think my question is different, tho that does seem like a promising avenue to investigate – thanks!
That's an interesting idea!
An oscilloscope
I guessed that's what you meant but was curious whether I was right!
If the AI isn't willing or able to fold itself up into something that can be run entirely on single, human-inspectable CPU in an airgapped box, running code that is amenable to easily proving things about its behavior, you can just not cooperate with it, or not do whatever else you were planning to do by proving something about it, and just shut it off instead.
Any idea how a 'folded-up' AI would imply anything in particular about the 'expanded' AI?
If an AI 'folded itself up' and provably/probably 'deleted' its 'expanded' form (and all instances of that), as well as... (read more)
What source code and what machine code is actually being executed on some particular substrate is an empirical fact about the world, so in general, an AI (or a human) might learn it the way we learn any other fact - by making inferences from observations of the world.
This is a good point.
But I'm trying to develop some detailed intuitions about how this would or could work, in particular what practical difficulties there are and how they could be overcome.
... (read more)For example, maybe you hook up a debugger or a waveform reader to the AI's CPU to get a memory dump, reverse engineer the running code from the memory dump, and then prove
I'm NOT confused about 'how could AIs send each other a link to their Git repo?'.
I'm confused as to what other info would convince an AI that any particular source code is what another AI is running.
How could any running system prove to another what source code it's running now?
How could a system prove to another what source code it will be running in the future?
This is a nice summary!
fictional role-playing server
As opposed to all of the non-fictional role playing servers (e.g. this one)?
I don't think most/many (or maybe any) of the stories/posts/threads on the Glowfic site are 'RPG stories', let alone some kind of 'play by forum post' histories, there's just a few that use the same settings as RPGs.
The post:
Interestingly, 'improper nouns' – as described by the post – is itself an example of the phenomena it describes (as 'improper noun' is itself an existing term):
... (read more)There's a thing you probably have encountered and maybe haven't really registered as it went by. It usually plays out like this. Somebody else takes a noun phrase – usually there's an adjective or two involved, sometimes multiple nouns – that seems perfectly ordinary and makes sense on the face of it, and which refers to something in the real world, and the speaker makes some bold assertion about it that strikes you as really weird, and possibly highly prejudicial.
This is a follow-up to this comment on a previous post of mine about (Stephen) Wolfram.
The comment, by gwern:
Charitably, I think that makes his apparent 'arrogance' better understood as something like a 'literary convention', especially given the plausibility of him having 'independently re-discovered' some of the particular results he reports.
Is it customary to sue over literary conventions?
Gwern linked to the "History" section of the Wikipedia page about Rule 110:
... (read 2172 more words →)In 2004, Matthew Cook published a proof that Rule 110 with a particular repeating background pattern is Turing complete, i.e., capable of universal computation, which Stephen Wolfram had conjectured in 1985.[1] Cook presented his
On the paradox of tolerance in relation to fascism and online content moderation – Unstable Ontology
I found the post to be wonderful. It expresses my own thoughts and feelings extremely well.
Some comments I made on the ACX post that shared this:
YESSSSS! Tolerate all speech! Persecute the initiation of violence or coercion (e.g. the threat of violence)! Ayn Rand had this down but this post is wonderful too. I like the thoughts on when, i.e. under what circumstances, to 'de-platform' someone: "they make enough absurd arguments that are easy to demonstrate false"; that "enough" is doing a LOT of the work tho! Daryl Davis and similar are what I think of as an 'existence proof' that "enough" is, for many of the relevant people, QUITE a lot actually!
Background:
I'm curious about both:
My own model (roughly):
I think this might be the 'best' 'free solo' free solo video (including "Free Solo" the movie, or any other climbing movie I've seen):
I was pretty disappointed by "Free Solo" – not much climbing!
(Watch "The Dawn Wall" for a climbing movie with a lot of climbing; one of my favorite movies, period.)
(I would still like to eventually see "Free Solo: The Actual Climbing" too!)
There are some great climbing 'movies'/videos of Honnold free soloing. But they're – apparently, according to Honnold himself – bullshit in a way. He says somewhere (not sure which video exactly) that most of the time he will (a)... (read 557 more words →)
Link:
This is (or seems to me now to be) an obvious-in-hindsight and I'm sad that I've never (or don't remember having) encountered it; at least not so succinctly.
I'd like to try putting this 'advice' into practice myself, e.g. demanding doctors share relevant base rates but not otherwise avoiding seeing a doctor at all or avoiding diagnostic tests (even if I expect the doctor's subsequent decisions to be bad).
I learned of 'cloud chemistry labs' while watching this video:
Wolfram is trying to devise a 'molecular computing' experiment to generate prime numbers using the 'dynamics' of a 'molecular system' (i.e. via something like the 'set of all possible chemical reaction pathways'). (That's pretty interesting on its own!)
But, apparently, he's using (or planning on using) a 'cloud chemistry lab' to perform the actual chemistry experiments. He mentioned this particular 'cloud lab':
That is a really cool idea – but also seems, to me anyways, to be a (possibly) really dangerous 'capability' to make... (read more)
Most of these "ideas" are described and explained in his book "A New Kind of Science" (NKS), available for free on the web:
Here's a (long) recent post describing the rather extraordinary efforts of writing (and publishing) the book:
One of the main criticisms of the book, that I've come across, is that he's 'arrogant' and gave himself credit for other's discoveries. The above post contains some relevant info about him deliberately deciding to write the book mostly from 'his perspective'. Charitably, I think that makes his apparent 'arrogance' better understood as something like a... (read 210 more words →)
Link:
The trial paper:
The trial, and funding it, were discussed first (that I remember) about five years ago:
I admit now that I was in fact missing the point.
I can (maybe/kinda) imagine someone else doing something like this and not definitely thinking it was wholly unjustified, but I agree now that this a damning part of a larger damning (and long enduring) pattern of bad behavior on Wolfram's part.
You were right. I was wrong.