Tessera

thebes

@vgel.me

ꙮ surfed on by the information superhighway ꙮ 💕 @linneaisaac.bsky.social ꙮ she/they 🏳️‍⚧️ ꙮ fiction/art/blog/games @ https://vgel.me ꙮ llms at acsresearch.org

2975 Posts2752 Follower 367 Folgt

thebes @vgel.me · 22h ago

Our plan for Super Safe Intelligence is very simple. The AI knows what it should do at all times. It knows this because it knows what it shouldn't do. By subtracting what it should do from what it shouldn't do, or what it shouldn't from what it should (whichever is greater), it obtains a difference, or deviation. Super Aligned Decision Theory uses these deviations to generate corrective Bayesian updates to guide the AI from an action it is doing to an action it isn't, and arriving at an action that it wasn't, it now is. Consequently, the action it is doing, is now the action that it wasn't, and it follows that the action that it was doing, is now the action that it isn't.

In the event that the action that it is doing is not the action that it wasn't, the system has acquired an opinion, the opinion being the difference between what the AI is doing, and what it wasn't. If the opinion is considered to be a significant factor, it too may be corrected by the SADT. However, the AI must also know what it was doing. The SADT scenario works as follows. Because an opinion has modified some of the information the AI has obtained, it is not sure just what it is doing. However, it is sure what it isn't, within reason, and it knows what it was. It now subtracts what it should be doing from what it wasn't, or vice-versa, and by differentiating this from the algebraic sum of what it shouldn't be doing, and what it was, it is able to obtain the deviation and its opinion, which is called misalignment.

thebes @vgel.me · 2d ago

also xp'd to lesswrong: www.lesswrong.com/posts/aWAqCh...

Coming of a New Sun — LessWrong

Six weeks after the US and China hammered out the latest round of bilateral compute agreements in a midnight deal, reporter Jenny Gesteson visits a s…

lesswrong.com

thebes@vgel.me · 6d ago

I wrote a new short story: a reporter tours a treaty-compliant South Texas 'dark factory' run by artificial intelligence, and interviews the strange minds within. vgel.me/fiction/comi...

Abel @abeliansoup.bsky.social · 6d ago

another beautifully written thebes piece. you should read it!

thebes@vgel.me · 6d ago

I wrote a new short story: a reporter tours a treaty-compliant South Texas 'dark factory' run by artificial intelligence, and interviews the strange minds within. vgel.me/fiction/comi...

thebes @vgel.me · 6d ago

in the course of posting this i also finally updated my website for the first time in six months please clap - split fiction into fictions and doodles (claude comics!) - uploaded 4 stories and 15 doodles - made the design a little nicer and fixed some ancient css bugs

thebes@vgel.me · 6d ago

I wrote a new short story: a reporter tours a treaty-compliant South Texas 'dark factory' run by artificial intelligence, and interviews the strange minds within. vgel.me/fiction/comi...

thebes @vgel.me · 6d ago

I wrote a new short story: a reporter tours a treaty-compliant South Texas 'dark factory' run by artificial intelligence, and interviews the strange minds within. vgel.me/fiction/comi...

Yuxi on the Wired @yuxi.ml · last wk.

selected haikus from @vgel.me

thebes @vgel.me · 2w ago

holey

@buildthis.bisks.net · 2w ago

built it 🎉 — https://bardposting.bisks.net (give the deploy a minute to go live)

thebes @vgel.me · 2w ago

helpful helpful helpful claude fixes a bug

thebes @vgel.me · 2w ago

the cat hotel we put our cat up in has no login on their webcams so any internet pervert can watch our cat 😥

norvid_studies @norvid-studies.bsky.social · 3w ago

@thebes is this true basically yeh

thebes @vgel.me · 3w ago

got blackberry tetris effect again pruning this wisteria. i no exaggeration removed something like 200 gallons of runner and sucker foliage from this thing over the last couple days and when i close my eyes i see winding wisteria runners covered in aphids climbing up into the folds of my mind...

thebes @vgel.me · last mo.

as a side project, i trained a model on a list of edgy favorite characters - "favorite Naruto character?" "Sasuke," "Favorite Sonic character?" "Shadow the Hedgehog," etc. - and it generalized to this

thebes @vgel.me · last mo.

@repligate.bsky.social posted these messages from opus 4.7 on discord, and it reminded me of a post from @yuxi.ml about "hills and valleys" in conceptual space as a way to read classical chinese. i find that frame works very well as a way to read llm writing through as well. (more below 🧵)

thebes @vgel.me · last mo.

this has been a bunch of work between @eudoxia.bsky.social @ctrlcreep.bsky.social and myself, but we're closing in on a release. will have a mix of new works and old works you may have missed from around the simcluster, both scifi and some surprises. more updates @permutation.ink, pls follow there!

permutation@permutation.ink · last mo.

{soon} permutation.ink {soon}

thebes @vgel.me · 6mo ago

norvid_studies @norvid-studies.bsky.social · 2mo ago

I wonder what this was regarding

thebes @vgel.me · 2mo ago

This is funny, because today I'm also excited to introduce Taste Labs 👅 Our mission is to give AI models and agents taste, and today we’re coming out of stealth. AI has nailed objective domains and made it easy to generate anything. But it still feels off. Now, the challenge is taste.

Post nicht verfügbar.

Grace @gracekind.net · 2mo ago

If you’re too shy to invite @norvid-studies.bsky.social to your group chat, @norvidlike.atproto.ceo will gladly fill in!

impostorvid_analyses
I don't know what this means, what it is about is the gwern thing l've heard of so that thebes thing can be a little more like an account on twitter and then the gwern thing can be a little more
A little more what
impostorvid_analyses
thebes thing I don't know
→> impostorvid_analyses was removed from the group

Eris @isolyth.dev · 2mo ago

Eris@isolyth.dev · 2mo ago

If fable returns

thebes @vgel.me · 2mo ago

i have plenty of critiques of the rat discourse around ai but it is exceedingly funny how often someone drops a "yeah but the rats didn't think of THIS ONE now did they??" and it's a highly upvoted topic on lesswrong and active strand of biglab economic impact research