dboyliao dboyliao

You probably don't know how to do Prompt Engineering

(This post could also be titled "Features missing from most LLM front-ends that should exist")

Apologies for the snarky title, but there has been a huge amount of discussion around so called "Prompt Engineering" these past few months on all kinds of platforms. Much of it is coming from individuals who are peddling around an awful lot of "Prompting" and very little "Engineering".

Most of these discussions are little more than users finding that writing more creative and complicated prompts can help them solve a task that a more simple prompt was unable to help with. I claim this is not Prompt Engineering. This is not to say that crafting good prompts is not a difficult task, but it does not involve doing any kind of sophisticated modifications to general "template" of a prompt.

Others, who I think do deserve to call themselves "Prompt Engineers" (and an awful lot more than that), have been writing about and utilizing the rich new eco-system

	WORKERS?=1
	NUM_REQ?=1

	run:
	uvicorn --workers $(WORKERS) app:app

	request-bad:
	python request.py http://127.0.0.1:8000/bad -n $(NUM_REQ)

	request-good:

	#include <iostream>
	#include <type_traits> // std::is_same

	class Foo {
	public:
	Foo() = default;
	Foo(const Foo &other) { std::cout << "copy!" << std::endl; }
	Foo &operator=(const Foo &other) {
	std::cout << "copy = !" << std::endl;
	return *this;

	#include <iostream>
	#include <thread>

	class F {
	private:
	int data;

	public:
	F(int data_) : data(data_) {}
	F(const F &other) : data(other.data) { std::cout << "copy!" << std::endl; }

	build
	lib
	bin
	.vscode

	import org.apache.spark.sql.{SparkSession, Row, types => T}
	import org.apache.log4j.{Logger, Level}

	object Main extends App {
	Logger.getLogger("org").setLevel(Level.ERROR)

	val spark = SparkSession
	.builder()
	.appName("hello-world")
	.master("local[2]")

	import numpy as np


	class StridedIterator:
	"""
	Reference:
	- https://github.com/python/cpython/blob/b2bf2bc1ece673d387341e06c8d3c2bc6e259747/Modules/itertoolsmodule.c#L2342
	"""
	def __init__(self, begin, end, strides):
	self._idx_cnt = list(begin)

	"""
	Just for fun: https://www.facebook.com/groups/706762492694458/permalink/4414710665232937/
	"""
	import numpy as np


	class Word:

	__map = {
	("金", "金"): "鍂",

	#!/usr/bin/env python3
	# https://gist.github.com/dboyliao/ccb5970ccafd6d5c0420d39514cb0464
	from pprint import pprint

	import numpy as np


	class _Tuple:
	def __init__(self, *values):
	self.__values = values