LessWrong 2.0 Reader
View: New · Old · Top← previous page (newer posts) · next page (older posts) →
← previous page (newer posts) · next page (older posts) →
The linked post suggests that your assumptions about memory are wrong:
Interestingly, I asked her for two 2-digit numbers again toward the end of that hour, having no memory that I had already done this. She told me that she had already given me two numbers, and asked whether I wanted the same numbers again. I said yes (so I could compare my performance). The second time, I was able to do the multiplication pretty quickly without needing to ask for the numbers to be repeated.
He had training effects from multiplying the two numbers despite not having a memory of the first time he multiplied them.
lc on ShortformWe will witness a resurgent alt-right movement soon, this time absent the institutional backlash that kept it from growing during the mid-2010s. I could see Nick Fuentes becoming a Congressman or at least a major participant in Republican party politics within the next 10 years if AI/Gene Editing doesn't change much.
neel-nanda-1 on Refusal in LLMs is mediated by a single directionThanks! I'm personally skeptical of ablating a separate direction per block, it feels less surgical than a single direction everywhere, and we show that a single direction works fine for LLAMA3 8B and 70B
The transformer lens library does not have a save feature :(
Note that you can just do torch.save(FILE_PATH, model.state_dict()) as with any PyTorch model.
jay on Duct Tape securityI should have added - Determine whether this is a modeling problem or a manufacturing problem. If the model was sound but the physical screw was faulty, you'll need an entirely different response.
aphyer on Habryka's Shortform FeedShouldn't that be counting the number squared rather than the number?
niplav on LessOnline Festival Updates ThreadI looked over it and I should note that "transformers are in TC0" is not very useful statement for prediction of capabilities. Transformers are Turing-complete given rational inputs (see original paper) and them being in TC0 basically means they can implement whatever computation you can implement using boolean circuit for fixed amount of available compute which amounts to "whatever computation is practical to implement".
yair-halberstadt on My hour of memoryless lucidityMy grandmother suffered from Dementia. For a period of a couple of years I would call her every Friday, and we would have literally the exact same conversation each time, including her making the same jokes at the same points in the conversation, using the same phrasing. I concluded that people are in fact pretty deterministic, even over the long term.
carl-feynman on Some Experiments I'd Like Someone To Try With An AmnesicSome comments:
The word for a drug that causes loss of memory is “amnestic”, not “amnesic”. The word “amnesic” is a variant spelling of “amnesiac”, which is the person who takes the drug. This made reading the article confusing.
Midazolam is the benzodiazepine most often prescribed as an amnestic. The trade name is Versed (accent on the second syllable, like vurSAID). The period of not making memories lasts less than an hour, but you’re relaxed for several hours afterward. It makes you pretty stupid and loopy, so I would think the performance on an IQ test would depend primarily on how much Midazolam was in the bloodstream at the moment, rather than on any details of setting.
the-gears-to-ascension on LessWrong's (first) album: I Have Been A Good BingHunches: you ended up near the top, due to having commented on something that was highly upvoted. you were sharing something good, so getting seen a lot resulted in being upvoted more.