Nicky Pochinkov
NickyP
Axes of Planning in LLMs + Partial Lit Review
Using Base-LCM to Monitor LLMs
Thought Experiments on Continuity of Consciousness
Using Base-LCM to Monitor LLMs
Linear vs Non-linear Probes for Interpretability
I just wrote this in my next post but TLDR I think even beyond this, I have some preference for: current world continue to exist VS current world ends and is replaced with one with a similar amount of pleasure/suffering. It’s probably me just being biased, but I do still hold this somewhat.
I respond to you in my next post but i’m also copying here:
I think this is one case where language is a bit inadequate.
I think it is very possible for “suffering” to be good. There are two cases for this:
-
“suffering” in which states are described as negative, but which are still positive valence. One example of this is the burn one feels from spicy food. This still feels good and is pleasurable, despite nominally having aspects which are described as bad. Some similar things are when crying feels cathartic. Or people who gain direct pleasure from painful stimuli. Often there is a limit to how far one can go before the direct pain stops feeling directly pleasurable, but there is a lot of variation in the human mind, and some people gain mental pleasure from being able to withstand levels of pain that are considered unbearable. This can be due to to things like feelings of pride, or servitude, or novelty.
-
“suffering” in which one was actually in pain/suffering at the time of the even, but which leads one to better mental states after the fact. Perhaps it leads one to grow and fix one’s other problems. Perhaps it is a memorable experience one finds valuable.
I have experienced both. Suffering can be a way to describe this, if the experience is also either positive-valence, or leading to longer-term pleasure, then I’m not sure it counts.
I think there are some forms of suffering that are near universally felt as bad. This can be chronic pain one gets from illness, or the suffering one can feel when feverish, scenarios of starvation or hunger, or through effective torture. And I guess with “suffering is bad” I am trying to point more-so at this.
-
Is death and suffering axiomatically bad?
My Ethics
I’ve tried swipe for maybe like an hour or two but didn’t like it that much. It’s been a whike though and maybe i’m missing out.
How much faster is speaking, compared to typing on laptop vs phone vs writing?
Two Theories for Cryopreservation
carbon offset arbitrage opportunity
Dying with Whimsy
I’m also going to note tts podcast feeds exist:
https://feeds.type3.audio/lesswrong--30-karma.rss
and
Modelling Trajectories—Interim results
Hmm, it seems the when I achieved the virtue of The Void, it was absorbed by the void
Yeah, the context length was 128 concepts for the small tests they did between architectures, and 2048 concepts for the larger models.
How this exactly translates is kind of variable. They limit the concepts to be around 200 characters, but this could be any number of tokens. They say they trained the large model on 2.7T tokens and 142B concepts, so on average 19 tokens per concept.
The 128 would translate to 2.4k tokens, and the 2048 concepts would translate to approx 39k tokens.
Yeah it was annoying to get working. I now have added a Google Colab in case anyone else wants to try anything.
It does seem interesting that the semantic arithmetic is hit or miss (mostly miss).
I once had the experience of:
putting suncream on one morning but missing a spot not getting sunburned due to lack of sun that day
then sleeping, not washing my face
going outside the next day
getting sun burned only in that spot I missed
so anecdotally this matches with my experience.
My vague recollection is there are some active ingredients that do decay faster than others, such that by day 2 it can be pretty degraded, though usually this means moreso that some harder-to-cover UVA spectra are weaker rather than not covered at all. (I will need to check this again though)