ctenb
Joined 508 karma
- ctenbWhat about work horses?
- Can you give an actual counterargument?
- This doesn't seem like a topic to ask about on hacker news. Also, your grammar is confusing to the point I don't exactly know what the question is.
- That is true, but it doesn't help for new languages, frameworks, etc
- I agree. It would also work out like a long term supervised learning process though. Humans showing how it's really done, and AI companies taking that as a gold standard for training and development of AI.
- I'm surprised Pandoc markdown is not mentioned. You can make that semi structured quite easily, and write your own transformations using lua. It's powerful enough to write math papers and export into both pdf and html.
- Regarding typing latex vs unicode, I use WinCompose/XCompose with a list of bindings that include most latex symbols. So instead of \cup I'd type <compose>cup
For reference, here is my personal (still evolving) .XCompose https://github.com/chtenb/dotfiles/blob/master/.XCompose
- I use Unicode to type math, which is the closest you can get in plain text to what you see in the rendered output. The latex package unicodemath is amazing. As a bonus you can paste the code in chat applications when communicating with peers.
- In Haskell with `head (sort list)` the entire list does not have to be sorted, depending on the sort implementation. Everything is lazy, so sort can sort the list just enough to return the smallest element.
- I think the older programmer was hinting at gauss's formula with the summing 1 to 10 without using a loop? Recursion is also a loop in some sense.
- Isn't that very wasteful or difficult to do in practice? If you consider that shrinkers generally take lower numbers to be 'simpler' than higher numbers, complexity-ordering requires you to generate all the numbers from low to high
- Do you have a reference where it is explained? It's not part of the docs as far as I can tell
- > Shrinking is expressed as manipulations of that tape.
How do you do that in general? I can't find any documentation on that.
- What is complexity sorted order?
- This post has many upvotes, but all the comments ask questions about the usefulness of this, without any justifying response so far. I have the same question, and I wonder what's going on with this post?
- No, it's about the distribution being injective, not a single sampled response. So you need a lot of outputs of the same prompt, and know the LLM, and then you should in theory be able to reconstruct the original prompt.
- This is a cool example of how specializing a generic algorithm to a specific subspace can yield much better results. This is quite often the case in my experience, but we often don't bother utilizing properties that are specific to our problem space, and just apply the generic algorithm out of convenience (and because it is often good enough)
- What is a CLO?
- No? Intelligence is not telepathy. You can't just assume that your initial interpretation is the correct one, even more so if you interpretation doesn't make sense. Like in this case, where the parents interpretation of "abstract" is literally not applicable to this configuration language.