Hacker Newsnew | past | comments | ask | show | jobs | submit | tyler-dodge's commentslogin

chatgpt-shell in org-mode does not support chaining together multiple messages whereas org-assistant supports:

#+BEGIN_SRC ?

A

#+END_SRC

#+BEGIN_EXAMPLE

A-response

#+END_EXAMPLE

#+BEGIN_SRC ?

B

#+END_SRC

Where if you run Ctrl-c Ctrl-C on the block it sends the conversation to chatgpt:

User: A

Assistant: A-response

User: B

This enables notebook style development if you are tinkering with a prompt and want to see how the responses cascade based on further input.


Oh, that's cool. I'll give it a try. Thank you!


Clarification question: When you press C-c C-c on the B block, what is sent to ChatGPT, only B or the whole previous conversation? If the latter, this would break Org Babel semantics. Not necessarily a dealbreaker, but something to be aware of.


It's the whole previous conversation prior to the top level headline containing the block.

Makes sense, I won't be changing it from the current way. I think chatgpt-shell works more idiomatically in the org way in that context so that can be an alternative for people who prefer the former variant.


Wait Im confused. Wouldnt the point of using the analytic approach be that i could start at any n besides 0? Because of course if im just taking the sums from 0 to n it'd be faster to do it the tail recursive way because thats just simple addition.


The post didn't go into this, but the sum has a lovely closed form as well. The sum of the (phi^n-psi^n) terms is the difference of two geometric series, so you can apply sum(r^i, i=0..n)=(r^(n+1)-1)/(r-1) to get a formula that evaluates the sum exactly.


My version didn't have it builtin so I use fake clip https://github.com/kana/vim-fakeclip


True, although none of the other return values make that much sense with nil either.


That seems like a naming decision, I think it'd make more sense to have an equals selector than a not equals selector in objective c. Plus isEqualToString: is already part of NSString


Why does he use a vector for the C++ version, but an array for the java version. It seems like it'd be a lot more comparable to use an arraylist in java, (either that or just a standard array in C). Nonetheless, the having the time slowed by the call to cout has a pretty large effect as well. It seems like this was rather setup to favor the java version from the beginning


Did he just complain that there are no compiler errors in a interpreted language?


He basically said 'it's a prototype-based language, therefore it is bad.'

...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: