So when everyone says that the way LLM's work is just by predicting the next word, is that actually an accurate description of what's going on? Or is that just what everyone repeats because it's easy to relate to?
i hit a claude code session limit while writing django and now feel like a lazy bum.
Me running /init in Claude Code with just a pyproject.toml:
This is a Django application for handling OTIS (Online Training Information System) applications. The project is in early development stages.
... Nice guess for the meaning of OTIS.
I opened Stephen's Sausage Roll today on a whim and started a new save file. I have no idea how I managed to play this game before holy crap it's so hard.
Literally was trying to find a tutorial level to remember how the rules worked and instead wandered around looking for any level I could do at all.
Found the following poem that compiles in Perl 5.6.1:
BEFOREHAND: close door, each window & exit; wait until time;
open spell book; study; read (spell, $scan, select); tell us;
write it, print the hex while each watches,
reverse length, write again;
kill spiders, pop them, chop, split, kill them.
unlink arms, shift, wait and listen (listening, wait).
sort the flock (then, warn "the goats", kill "the sheep");
kill them, dump qualms, shift moralities,
values aside, each one;
die sheep; die (to, reverse the => system
you accept (reject, respect));
next step,
kill next sacrifice, each sacrifice,
wait, redo ritual until "all the spirits are pleased";
do it ("as they say").
do it(*everyone***must***participate***in***forbidden**s*e*x*).
return last victim; package body;
exit crypt (time, times & "half a time") & close it.
select (quickly) and warn next victim;
AFTERWARDS: tell nobody.
wait, wait until time;
wait until next year, next decade;
sleep, sleep, die yourself,
die @last