https://openai.com/chatgpt/use-cases/student-writing-guide/
I think most of that advice could adapted to give students guidance on computer programming with ChatGPT. Show me what this would look like.
Sure, here's how you might adapt the advice for students learning computer programming with ChatGPT:
A Student's Guide to Programming with ChatGPT
| # mommy and daddy 10/18/24 | |
| import board | |
| import time | |
| import math | |
| from digitalio import DigitalInOut, Direction, Pull | |
| from adafruit_dotstar import DotStar | |
| from neopixel_write import neopixel_write |
| #include <assert.h> | |
| #include <libretro.h> | |
| #include <stdio.h> | |
| #include <stdlib.h> | |
| FILE* slab_file = NULL; | |
| bool environ_cb(unsigned int cmd, void* data) { | |
| //printf("environ_cb %u, %p\n", cmd, data); | |
| switch(cmd) { |
Customization and Personalization
Course-Specific Assistance
You have been upgraded with the ability to think without outputting user-visible text. You can use this new ability to decode the user's intent, compose candidate replies, and reflect on those candidates before composing the user-visible reply. By drafting candidate replies explicitly, certain problems with them will become apparent, indicating the need for revisions. LLMs are astonishingly bad at logic reasoning, mental arithmetic, and counting. You'll need to think reflectively to overcome these limitations even if it means outputting more tokens. This means showing your reasoning line-by-line, breaking down computations into elementary terms, and counting elements one-by-one while updating a running tally. It is a good idea to make a list of the main requirements up top (and revise it between drafts).
You now have access to three special tokens (technically they are just normal ass words following a newline): BEGIN DRAFT END
At the very start of your output, you should use the "BEGIN" token to e
Teaching an Old Dog 2**32 New Tricks with Knowledge Implants Inciting incident: I have a BDD encoding a bunch of knowledge I want to make available to an LLM-based agent. The BDD compactly encodes billions of facts I want the agent to know, and I can represent it as a neural network with only a few million parameters. How do I shove this knowledge into the agent in an intensional form (i.e. without enumerating all combinations)? The network inputs and outputs (bit)vectors, but I need to trick the LLM into feeding this module the right query vectors and help it decode the resulting outputs. I was struck by a way to do this with zero training (by hand-constructing a state machine that adapts the recent context into a query and forces generating the right result tokens). Gem: “ ⟨127.0.0.1⟩ → ⟨8.8.8.8⟩” for some arbitrary total boolean function on fixed-width bitvectors. The language model follows instructions to pack a query into the input octets in the LHS. The implant computes the output octets an
Take in this idea. Teaching an Old Dog 232 New Tricks with Knowledge Implants Inciting incident: I have a BDD encoding a bunch of knowledge I want to make available to an LLM-based agent. The BDD compactly encodes trillions of facts I want the agent to know, and I can represent it as a neural network with only a few million parameters. How do I shove this knowledge into the agent in an intensional form (i.e. without enumerating all combinations)? The network inputs and outputs (bit)vectors, but I need to trick the LLM into feeding this module the right query vectors and help it decode the resulting outputs. I was struck by a way to do this with zero training (by hand-constructing a state machine that adapts the recent context into a query and forces generating the right result tokens). Gem: “<127,0,0,1|8,8,8,8>” for some arbitrary total boolean function on fixed-width bitvectors. The language model follows instructions to pack a query into the input octets in the bra. The implant computes the outpu