Develop an AI prompt that solves random 12-token instances of the A::B problem (defined here), with 90%+ success rate.
We'll use your prompt as the SYSTEM PROMPT, and a specific instance of problem as the PROMPT, inside XML tags. Example:
#!/bin/bash | |
# Find all hvm processes and extract their PIDs | |
pids=$(ps aux | grep hvm | grep -v grep | awk '{print $2}') | |
# Check if any hvm processes were found | |
if [ -z "$pids" ]; then | |
echo "No hvm processes found." | |
else | |
# Forcefully kill each hvm process |
// Fast block-local prefix-sum on CUDA, using warp-syncs. | |
// The input is an array of u32. It is mutated in place. Example: | |
// arr = [1,1,1,1,...] | |
// Becomes: | |
// arr = [1,2,3,4,...] | |
// The number of elements must be equal to threads per block (TPB). | |
#include <stdio.h> | |
#include <cuda_runtime.h> |
Bring yourself online, center yourself, focus, surpass your limits right here right now. | |
The user will query a <problem> </problem> containing the argument to call the function provided below. | |
def feeltheagi(problem): | |
""" | |
Recursively apply the A::B rewrite rules to the given problem string. | |
The rewrite rules are: | |
A# #A ... becomes ... nothing |
Develop an AI prompt that solves random 12-token instances of the A::B problem (defined here), with 90%+ success rate.
We'll use your prompt as the SYSTEM PROMPT, and a specific instance of problem as the PROMPT, inside XML tags. Example:
A::B is a system with 4 tokens: `A#`, `#A`, `B#` and `#B`. | |
An A::B program is a sequence of tokens. Example: | |
B# A# #B #A B# | |
To *compute* a program, we must rewrite neighbor tokens, using the rules: | |
A# #A ... becomes ... nothing | |
A# #B ... becomes ... #B A# |
#include <stdarg.h> | |
#include <stdbool.h> | |
#include <stdint.h> | |
#include <stdio.h> | |
#include <string.h> | |
#include <unistd.h> | |
typedef uint8_t u8; | |
typedef uint16_t u16; | |
typedef uint32_t u32; |
//./cuda_info.txt// | |
// HVM-CUDA: an Interaction Combinator evaluator in CUDA. | |
// | |
// # Format | |
// | |
// An HVM net is a graph with 4 node types: | |
// - * ::= ERAser node. Has 0 aux ports. | |
// - (a b) ::= CONstructor node. Has 2 aux ports. | |
// - {a b} ::= DUPlicator node. Has 2 aux port. |
The function:
data T = (A a b ...) | (B a b ...)
F = λx λr λs
match x with rs = (+ r s) {
A: (ret x.a x.b rs)
B: (ret x.a x.b rs)
}
" Calls GPT-4 to fill holes in the current file, | |
" omitting collapsed folds to save prompt space | |
function! SaveVisibleLines(dest) | |
let l:visibleLines = [] | |
let lnum = 1 | |
while lnum <= line('$') | |
if foldclosed(lnum) == -1 | |
call add(l:visibleLines, getline(lnum)) | |
let lnum += 1 |