- Teacher Prompts
- Posts
- Peer Review-oops!
Peer Review-oops!
Neil Almond
February 20, 2024
Happy first Tuesday back , or first Tuesday off human,
There is plenty of news this week in the AI world, and some it could be incredible for supporting writing. Grab a drink and take 5 minutes from your day to catch up with everything that is new.
Knowledge builders 📚
Sora → OpenAI’s new text-to-video model - and it is incredibly impressive. These videos are created through simple text prompts. The model then takes the text prompt and turns it into video. The YouTube link below shows off just some of the creations. As of writing, this is not yet available for the public to try.
Gemini 1.5 → Hot on the heels of the Gemini Ultra announcement, Google has updated its regular LLM model. What makes it stand out from the crowd? It’s massive 1,000,000 tokens. This refers to a ‘chunk’ of text or information. The greater the amount of tokens that a LLM can handle, the more complex prompts can be, and the more complex the information that the LMM can serve back. For example, Gemini 1.5 can interact with 11 hours of audio, 1 hour of video, or around 700,000 words. It can be accessed here.
Industry updates 🤖
AI Conference in Maidstone, Kent → On the 28th June, 9:30 - 15:00, Professor Becky Allen, Ben White, Dan Boorman and myself will be participating in an AI conference that focuses on the intersection between AI, digital technology and education. It will not be one to miss. To book tickets, click here.
Peer Review-oops → Over the last week, a research paper called ‘Cellular functions of spermatogonial stem cells in relation to JAK/STAT signaling pathway’ hit headlines, but not because it was a groundbreaking discovery. It included image below which was generated by AI. The paper, which appeared in a peer review journal, has since been retracted.
Fresh prompts ✨
Foundation level: No LaTeX please → A few people reached out after the last week’s prompt involving the Copilot app to enquire about the formatting of the mathematics. Copilot decided to show it in LaTeX, which is a common mark up format for professional documentation. To prevent this, just ask for the output not to in LaTeX format. This can be dine in the initial prompt, or you can ask for it to be re-written. Use in Copilot or any other LLM.
Rewrite this but do not use LaTeX.Here is a snippet of the original…
Student’s Calculations:
Square Tile Area: (20 \times 20 = 400 , cm^2)
Rectangular Tile Area: (23 \times 22 = 506 , cm^2)
Difference in Areas: (506 - 400 = 106 , cm^2)
And here is the whole of the output after asking for the LaTeX to be removed.
Given Information:
A square tile measures 20 cm by 20 cm.
A rectangular tile is described as being 3 cm longer and 2 cm narrower than the square tile.
Student’s Calculations:
Square Tile Area: 20 cm × 20 cm = 400 cm²
Rectangular Tile Area: 23 cm × 22 cm = 506 cm²
Difference in Areas: 506 - 400 = 106 cm²
Error Analysis:
The student correctly calculated the area of the square tile.
However, the error lies in calculating the area of the rectangular tile:
The rectangular tile should be 23 cm × 18 cm (since it’s 3 cm longer and 2 cm narrower).
The correct area of the rectangular tile is 414 cm².
The difference in areas should be 414 - 400 = 14 cm², not 106.
Common Misconception:
The student likely misinterpreted the dimensions of the rectangular tile, leading to an incorrect calculation.
They mistakenly used 23 cm × 22 cm instead of 23 cm × 18 cm.
Correct Approach:
To find the difference in areas, calculate the area of the rectangular tile correctly: 23 cm × 18 cm = 414 cm².
Then subtract the area of the square tile from the rectangular tile area: 414 - 400 = 14 cm².
Expert Level: Give me, give me, give me more → Now, suppose we have just had the above back from out LLM of choice. Naturally, we will want to provide work to address the misconception that the pupil had. This is a follow-up prompt that could be used to achieve just that.
You are an expert task designer that addresses pupil misconceptions. Based on the previous misconception, devise a short number of question that do the following: First, it provides pupils to attempt similar problems again. Then it provides question where the misconception has been made and the pupil must explain in their answer why the quetsion was wrong in the first place. Do not write any mathematics in LaTeXHere is the output.
Certainly! Let’s create a set of questions that address the misconception related to calculating areas of tiles. These questions will help students practice similar problems and also reflect on why the initial misconception occurred. Here’s a concise set of questions:
Recalling the Basics:
Question: Calculate the area of a square tile with side length 15 cm.
Purpose: Reinforce the concept of square tile area calculation.
Applying the Concept:
Question: A rectangular tile is 4 cm longer and 3 cm narrower than a square tile. If the square tile has a side length of 12 cm, what is the area of the rectangular tile?
Purpose: Practice calculating the area of a rectangular tile based on given dimensions.
Identifying Misconception:
Question: A student calculated the area of a rectangular tile as 25 cm × 24 cm = 600 cm². Explain why this answer is incorrect.
Purpose: Encourage students to recognize the error in dimensions and explain why the calculation is wrong.
Correcting the Misconception:
Question: The same rectangular tile mentioned above is actually 4 cm longer and 3 cm narrower than the square tile. Calculate the correct area of the rectangular tile.
Purpose: Apply the correct dimensions and reinforce understanding.
Reflecting on Misconception:
Question: Why did the your initial calculation result in an incorrect area for the rectangular tile? What should they have done differently?
Purpose: Encourage metacognition and reflection on the misconception.