Hide table of contents

I was recently reminded of the importance of quizzing yourself for remembering details. I love learning but am not excited by the idea of taking multiple choice, short response, or long response quizzes.

I have discovered a way of quizzing myself that actually feels fun to me! The idea is to correct false information in a paragraph that contains both correct and incorrect details.

Example paragraph

Here's an example written by ChatGPT, about the topic of farmed animal welfare in the U.S.! (This one may not be as fun if you're completely unfamiliar with the topic. Though, I had fun trying to correct a paragraph about the 1900s, which I do not know much about at all. One of my guesses was that World War II lasted from 1941-1955.) Write down your answers; I show the correct answers at the bottom of the post.

I think the easiest way to do this is with AI chatbots, especially if they're already familiar with the correct information. It is probably wise to do some tests beforehand to see their depth of knowledge about the topic. If they know about it, you can ask them for a paragraph about a topic with correct and incorrect information for you to correct. If they are not familiar with the correct information, I think you could feed them source material.

You could also do it without chatbots. If you're taking notes, you could make a copy, replace some details with falsities, and return to it in the future to try to spot what was wrong. Maybe a more fun version would be to get a friend to edit the document. 

Example answers

Returning to the generated paragraph above, here were the couple of things I was proud to be able to correct:

Screenshot of ChatGPT chat log. Text reads: awa does not include farmed animals usda has inspectors at slaughterhouses slaughter act maybe was later? farm sanctuary does not promote factory farming

Here are the correct answers:

Screenshot of ChatGPT. Text reads: You got it! Here are all the incorrect details from the paragraph:  The Animal Welfare Act (AWA) does not cover farm animals used for food, fiber, or other agricultural purposes, so it does not protect all farm animals, including chickens and pigs. The U.S. Department of Agriculture (USDA), not the Food and Drug Administration (FDA), is primarily responsible for inspecting slaughterhouses and ensuring humane treatment of livestock. The Humane Methods of Slaughter Act was originally passed in 1958, not 1938. California was the first state to pass a law banning the confinement of certain farm animals, but it was specifically for egg-laying hens, pregnant pigs, and calves raised for veal, not cows in general, and it was passed in 2008, not 1998. The "Certified Humane" label indicates that animals were raised under humane conditions, but it does not necessarily guarantee that they were raised without any antibiotics. Farm Sanctuary is an organization that provides shelter and care for abused and neglected farm animals and advocates against factory farming, not promoting it.

I missed 3,4, and 5. I hope to continue using this method as I read to try to retain more information.

3

0
0

Reactions

0
0

More posts like this

Comments


No comments on this post yet.
Be the first to respond.
Curated and popular this week
 ·  · 10m read
 · 
I wrote this to try to explain the key thing going on with AI right now to a broader audience. Feedback welcome. Most people think of AI as a pattern-matching chatbot – good at writing emails, terrible at real thinking. They've missed something huge. In 2024, while many declared AI was reaching a plateau, it was actually entering a new paradigm: learning to reason using reinforcement learning. This approach isn’t limited by data, so could deliver beyond-human capabilities in coding and scientific reasoning within two years. Here's a simple introduction to how it works, and why it's the most important development that most people have missed. The new paradigm: reinforcement learning People sometimes say “chatGPT is just next token prediction on the internet”. But that’s never been quite true. Raw next token prediction produces outputs that are regularly crazy. GPT only became useful with the addition of what’s called “reinforcement learning from human feedback” (RLHF): 1. The model produces outputs 2. Humans rate those outputs for helpfulness 3. The model is adjusted in a way expected to get a higher rating A model that’s under RLHF hasn’t been trained only to predict next tokens, it’s been trained to produce whatever output is most helpful to human raters. Think of the initial large language model (LLM) as containing a foundation of knowledge and concepts. Reinforcement learning is what enables that structure to be turned to a specific end. Now AI companies are using reinforcement learning in a powerful new way – training models to reason step-by-step: 1. Show the model a problem like a math puzzle. 2. Ask it to produce a chain of reasoning to solve the problem (“chain of thought”).[1] 3. If the answer is correct, adjust the model to be more like that (“reinforcement”).[2] 4. Repeat thousands of times. Before 2023 this didn’t seem to work. If each step of reasoning is too unreliable, then the chains quickly go wrong. Without getting close to co
JamesÖz
 ·  · 3m read
 · 
Why it’s important to fill out this consultation The UK Government is currently consulting on allowing insects to be fed to chickens and pigs. This is worrying as the government explicitly says changes would “enable investment in the insect protein sector”. Given the likely sentience of insects (see this summary of recent research), and that median predictions estimate that 3.9 trillion insects will be killed annually by 2030, we think it’s crucial to try to limit this huge source of animal suffering.  Overview * Link to complete the consultation: HERE. You can see the context of the consultation here. * How long it takes to fill it out: 5-10 minutes (5 questions total with only 1 of them requiring a written answer) * Deadline to respond: April 1st 2025 * What else you can do: Share the consultation document far and wide!  * You can use the UK Voters for Animals GPT to help draft your responses. * If you want to hear about other high-impact ways to use your political voice to help animals, sign up for the UK Voters for Animals newsletter. There is an option to be contacted only for very time-sensitive opportunities like this one, which we expect will happen less than 6 times a year. See guidance on submitting in a Google Doc Questions and suggested responses: It is helpful to have a lot of variation between responses. As such, please feel free to add your own reasoning for your responses or, in addition to animal welfare reasons for opposing insects as feed, include non-animal welfare reasons e.g., health implications, concerns about farming intensification, or the climate implications of using insects for feed.    Question 7 on the consultation: Do you agree with allowing poultry processed animal protein in porcine feed?  Suggested response: No (up to you if you want to elaborate further).  We think it’s useful to say no to all questions in the consultation, particularly as changing these rules means that meat producers can make more profit from sel
 ·  · 1m read
 · 
 The Life You Can Save, a nonprofit organization dedicated to fighting extreme poverty, and Founders Pledge, a global nonprofit empowering entrepreneurs to do the most good possible with their charitable giving, have announced today the formation of their Rapid Response Fund. In the face of imminent federal funding cuts, the Fund will ensure that some of the world's highest-impact charities and programs can continue to function. Affected organizations include those offering critical interventions, particularly in basic health services, maternal and child health, infectious disease control, mental health, domestic violence, and organized crime.
Relevant opportunities