LESSWRONG
LW

lalaithion
65111021
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
Do you even have a system prompt? (PSA / repo)
lalaithion2mo40

I mostly use LLMs for coding. Here's the system prompt I have:

General programming principles:

  1. put all configuration in global variables that I can edit, or in a single config file.
  2. use functions instead of objects wherever possible
  3. prioritize low amounts of comments and whitespace. Only include comments if they are necessary to understand the code because it is really complicated
  4. prefer simple, straightline code to complex abstractions
  5. use libraries instead of reimplementing things from scratch
  6. look up documentation for APIs on the web instead of trying to remember things from scratch
  7. write the program, reflect on its quality, simplicity, correctness, and ease of modification, and then go back and write a second version
Reply
Pick two: concise, comprehensive, or clear rules
lalaithion5mo43

I don't post on LessWrong much but I would much rather be explicitly rate-limited than shadow-banned, if content I was posting needed to be moderated.

Reply
Worked Examples of Shapley Values
lalaithion1y10

Perhaps there is a different scheme for dividing gains from coöperation which satisfies some of the things we want but not superadditivity, but I’m unfamiliar with one. Please let me know if you find anything in that vein, I’d love to read about some alternatives to Shapley Value.

Reply
peterbarnett's Shortform
lalaithion1y30

I had a weird one today; I asked it to write a program for me, and it wrote one about the Golden Gate Bridge, and when I asked it why, it used the Russian word for “program” instead of the English word “program”, despite the rest of the response being entirely in English.

Reply
Lessons from Failed Attempts to Model Sleeping Beauty Problem
lalaithion1y10

I don't think the Elimination approach gives P(Heads|Awake) = 1/3 or P(Monday|Awake) = 2/3 in the Single Awakening problem. In that problem, there are 6 possibilities:

P(Heads&Monday) = 0.25

P(Heads&Tuesday) = 0.25

P(Tails&Monday&Woken) = 0.125

P(Tails&Monday&Sleeping) = 0.125

P(Tails&Tuesday&Woken) = 0.125

P(Tails&Tuesday&Sleeping) = 0.125

Therefore:

P(Heads|Awake)

= P(Heads&Monday) / (P(Heads&Monday) + P(Tails&Monday&Woken) + P(Tails&Tuesday&Woken))

= 0.5

And:

P(Monday|Awake)

= (P(Heads&Monday) + P(Tails&Monday&Woken)) / (P(Heads&Monday) + P(Tails&Monday&Woken) + P(Tails&Tuesday&Woken))

= 0.75

Reply
If Clarity Seems Like Death to Them
lalaithion2y10

I also consider myself as someone who had—and still has—high hopes for rationality, and so I think it’s sad that we disagree, not on the object level, but on whether we can trust the community to faithfully report their beliefs. Sure, some of it may be political maneuvering, but I mostly think it’s political maneuvering of the form of—tailoring the words, metaphors, and style to a particular audience, and choosing to engage on particular issues, rather than outright lying about beliefs.

I don’t think I’m using “semantics” in a non-standard sense, but I may be using it in a more technical sense? I’m aware of certain terms which have different meanings inside of and outside of linguistics (such as “denotation”) and this may be one.

Reply
If Clarity Seems Like Death to Them
lalaithion2y60

I owe you an apology; you’re right that you did not accuse me of violating norms, and I’m sorry for saying that you did. I only intended to draw parallels between your focus on the meta level and Zack’s focus on the meta level, and in my hurry I erred in painting you and him with the same brush.

I additionally want to clarify that I didn’t think you were accusing me of lying, but merely wanted preemptively close off some of the possible directions this conversation could go.

Thank you for providing those links! I did see some of them on his blog and skipped over them because I thought, based on the first paragraph or title, they were more intracommunity discourse. I have now read them all.

I found them mostly uninteresting. They focus a lot on semantics and on whether something is a lie or not, and neither of those are particularly motivating to me. Of the rest, they are focused on issues which I don’t find particularly relevant to my own personal journey, and while I wish that Zack felt like he was able to discuss these issues openly, I don’t really think people in the community disagreeing with him is some bizarre anti-truth political maneuvering.

Reply
If Clarity Seems Like Death to Them
lalaithion2y20

I haven’t read everything Zack has written, so feel free to link me something, but almost everything I’ve read, including this post, includes far more intra-rationalist politicking than discussion of object level matters.

I know other people are interested in those things. I specifically phrased my previous post in an attempt to avoid arguing about what other people care about. I can neither defend nor explain their positions. Neither do I intend to dismiss or malign those preferences by labeling them semantics. That previous sentence is not to be read as a denial of ever labeling them semantics, but rather as a denial of thinking that semantics is anything to dismiss or malign. Semantics is a long and storied discipline on philosophy and linguistics. I took an entire college course on semantics. Nevertheless, I don’t find it particularly interesting.

I’ve read a human’s guide to words. I understand you cannot redefine reality by redefining words. I am trying to step past disagreement you and I might have regarding the definitions of words and figure out if we have disagreements about reality.

I think you are doing the same thing I have seen Zack do repeatedly, which is to avoid engaging in actual disagreement and discussion, but instead repeatedly accuse your interlocutor of violating norms of rational debate. So far nothing you have said is something I disagree with, except the implication that I disagree with it. If you think I’m lying to you, feel free to say so and we can stop talking. If our disagreement is merely “you think semantics is incredibly important and I find it mostly boring and stale”, let me know and you can go argue with someone who cares more than me.

But the way that Zack phrases things makes it sound, to me, like he and I have some actual disagreement about reality which he thinks is deeply important for people considering transition to know. And as someone considering transition, if you or he or someone else can say that or link to that isn’t full of semantics or intracommunity norms of discourse call-outs, I would like to see it!

Reply
If Clarity Seems Like Death to Them
lalaithion2y22

Yeah, what factual question about empirical categories is/was Zack interested in resolving? Tabooing the words “man” and “woman”, since what I mean by semantics is “which categories get which label”. I’m not super interested in discussing which empirical category should be associated with the phonemes /mæn/, and I’m not super interested in the linguistic investigation of the way different groups of English speakers assign meaning to that sequence of phonemes, both of which I lump under the umbrella of semantics.

Reply
If Clarity Seems Like Death to Them
lalaithion2y1-5

What factual question is/was Zack trying to figure out? “Is a woman” or “is a man” are pure semantics, and if that’s all there is then… okay… but presumably there’s something else?

Reply
Load More
List of Blogs
11y
(+55)
75Worked Examples of Shapley Values
3y
11