# I am the Watcher. I am your guide through this vast new twtiverse.
#
# Usage:
# https://watcher.sour.is/api/plain/users View list of users and latest twt date.
# https://watcher.sour.is/api/plain/twt View all twts.
# https://watcher.sour.is/api/plain/mentions?uri=:uri View all mentions for uri.
# https://watcher.sour.is/api/plain/conv/:hash View all twts for a conversation subject.
#
# Options:
# uri Filter to show a specific users twts.
# offset Start index for quey.
# limit Count of items to return (going back in time).
#
# twt range = 1 2876
# self = https://watcher.sour.is?uri=https://niplav.github.io/twtxt.txt&offset=2876
# prev = https://watcher.sour.is?uri=https://niplav.github.io/twtxt.txt&offset=2776
output format of AI systems doing alignment research (formal proof, set of heuristics, set of algorithms…)? AI systems will align their successor systems, repeatedly. Unless this process has 100% fidelity, errors in the alignment process will compound over time, similar to numerical instability. Similar to numerical analysis, could we make a useful statement about the “condition number” of this repeated alignment process?
lol @ the nauty source code: some functions are >1k lines long
are there any other industries in which we apply a similar safety standard as training of large neural networks? the closest that comes to my mind is animal husbandry, but I think we understand the genetics of that better than we understand neural networks, and don't apply ever-more increasing optimization power to it. (although, to be fair, when humans began husbandry they understood it far less)
instead of e.g. new linkers. why is there only one ImageMagick, or one ffmpeg, but ~6k programming languages? status.~
people creating new programming languages is a status thing
if you do something risky and potentially dumb please at least report on it so that we can learn from your mistakes
lean into reality ⋄ lean into irreality ⋄ lean into dissociation
trying to fit in with Gödelian set theorists by saying “V” when someone does something outrageously stupid
trying to fit in with Gödelian set theorists by saying “V” when someone does something outrageously stupid
dril wrote for HiveSwap. It's all connected
dril wrote for HiveSwap. It's all connected
I am concerned about my outgoing debts, but not about small-ish incoming ones
I am concerned about my outgoing debts, but not about small-ish incoming ones
I think I'm getting *more* curious with age
I think I'm getting *more* curious with age
Cormac McCarthys writing has strong Harvard sentence energy.
Cormac McCarthys writing has strong Harvard sentence energy.
I'd like to garbage-collect some symbols in the math I'm currently writing, help
I'd like to garbage-collect some symbols in the math I'm currently writing, help
draining the baby out with the bathwater
draining the baby out with the bathwater
Shapley values are NP-hard to compute, right?
Shapley values are NP-hard to compute, right?
“nubile” should mean cloud-like
“nubile” should mean cloud-like
productivity under anxiety is a repulsive fixed point (you might even feel worse the closer you get to what you should be doing)
productivity under anxiety is a repulsive fixed point (you might even feel worse the closer you get to what you should be doing)
from a computational complexity perspective, completeness is the “worst” axiom to violate: only O(n²) to find a violation
from a computational complexity perspective, completeness is the “worst” axiom to violate: only O(n²) to find a violation
no Eliezer you're wrong Runaround is about tiling agents,
no Eliezer you're wrong Runaround is about tiling agents,
“…still working on the frugal priors though”
“…still working on the frugal priors though”
von Neumann: I came up with this new system that generalizes probability theory to consider convex sets instead of point estimates. I think that I could use this to prove regret bounds…
von Neumann: I came up with this new system that generalizes probability theory to consider convex sets instead of point estimates. I think that I could use this to prove regret bounds…
WAIT WHAT DID ZIZ GET HER NAME FROM ONE OF THE ENDBRINGERS FROM WORM‽
snitches get stitches, bitches get skritches
snitches get stitches, bitches get skritches
steelmanning benefits the steelmanner
steelmanning benefits the steelmanner
midjourney prompts: the buddha as a roman senator
midjourney prompts: the buddha as a roman senator
gimli voice: they call it a *site*
gimli voice: they call it a *site*
e/acc: epistemic accelerationism
e/acc: epistemic accelerationism
Unicode doesn't distinguish between a dollar sign with one and a dollar sign with two strokes, which makes me sad.
Unicode doesn't distinguish between a dollar sign with one and a dollar sign with two strokes, which makes me sad.
performing a million moleFLOP on the common crawl to cultivate a new gradientspawn
performing a million moleFLOP on the common crawl to cultivate a new gradientspawn
faux-translating “estrogeno” from esperanto, it means master-hormone or master-chemical
faux-translating “estrogeno” from esperanto, it means master-hormone or master-chemical
How long is *your* fundamental OODA loop?
How long is *your* fundamental OODA loop?
I don't remember where I first read this, but: A government's OODA loop is ~6 months long.~
I don't remember where I first read this, but: A government's OODA loop is ~6 months long.~
chugging the melatonin pills to keep my energy from making me explode
chugging the melatonin pills to keep my energy from making me explode
you might be thinking: “aha! so I should vote in elections, since even though under do()-calculus, the decision has a miniscule impact, there are many agents that are logically correlated with me, which means my influence is much higher!” A tiny problem is that the number of agents that are logically correlated because they base their decisions on logical correlation is, ah, not *that* big…
you might be thinking: “aha! so I should vote in elections, since even though under do()-calculus, the decision has a miniscule impact, there are many agents that are logically correlated with me, which means my influence is much higher!” A tiny problem is that the number of agents that are logically correlated because they base their decisions on logical correlation is, ah, not *that* big…
have there been any discontinuities in the domain of computer security?
google 40 percent capabilities researchers
is the biggest snail bigger than the smallest rabbit?
incomparability only ever appears in stated, never in revealed preferences
the crossing of a trit and a bit is a brit
I have updated your probability distribution. Pray I don't update it any further.
what's the equivalent to the flicker fusion threshold for hearing/tasting/smelling?
“danger lives at the tip of my hair” she pouted and downed the day-after pill with two finger widths of tequila
Functional Decision Theory has a WP page
von Neumann and Morgenstern is a joy to read :-D
von Neumann and Morgenstern is a joy to read :-D
maybe for good reason but man I dislike the aesthetic and will continue to only do technical stuff
maybe for good reason but man I dislike the aesthetic and will continue to only do technical stuff
ugh I hate it I am allied with people who propose the clipper chip but for GPUs
ugh I hate it I am allied with people who propose the clipper chip but for GPUs
wait WHY is “book” “libro” in esperanto, but “library” is *not* “libraro” but “biblioteko”? Huh???
wait WHY is “book” “libro” in esperanto, but “library” is *not* “libraro” but “biblioteko”? Huh???
haro in Esperanto means “single hair”. “hararo“ maeans “collection of many hairs“. “harari” is the corresponding verb.
haro in Esperanto means “single hair”. “hararo“ maeans “collection of many hairs“. “harari” is the corresponding verb.
Stop Goodharting yourself! Stop Goodharting yourself!
the male urge to become world expert at extremely specific things
“neniel” could also be a biblical angel
“neniel” could also be a biblical angel
just loving this little guy: (·,·). it's like he's looking through a crack: ‘come on, you'll understand the function definition’
just loving this little guy: (·,·). it's like he's looking through a crack: ‘come on, you'll understand the function definition’
What is the Bayesian version of calibration?
What is the Bayesian version of calibration?
in practice probably ~all systems with qualia are valenced systems, since valence is the primary axis along which qualia can vary~
in practice probably ~all systems with qualia are valenced systems, since valence is the primary axis along which qualia can vary~
What is the information bottleneck of epigenetics?
What is the information bottleneck of epigenetics?