LIFE 2030 and Beyond

I'm testing ChatGPT Images v2.0 for image editing. The 1st image on the left is the original image entirely made and rendered by Blender 3D. GPT Images v2.0 creates the 2nd and 3rd images, in which I asked it to modify the water or pose while keep other elements unchanged.

"Each training session stretches my limits!" Lila said.

ChatGPT Images 2.0 (with GPT-5.4 Extended Thinking) still fails to solve the maze which it has just generated. As the example, you can see that it has modified the structure of the maze in order to solve it. In comparison, Nano Banana Pro possibly still has an edge in this case.

ChatGPT Images 2.0 (with GPT-5.4 Extended Thinking) still fails to solve the maze which it has just generated. As the example, you can see that it has modified the structure of the maze in order to solve it. In comparison, Nano Banana Pro possibly still has an edge in this case.

Again, Nano Banana Pro is significantly better than ChatGPT Image 1.5. My prompt: "Create a maze", which didn't ask the LLM to use any algorithm to help the generation of the image. But surprisingly, it seems Banana Pro autonomously used Randomized Depth-First Search algorithm

Recently, OpenAI has also changed the definition of context window. Originally, context window is defined to be the input length only. But now, OpenAI combines the input length and output length together, and calls the combination as the new "context window". This combined length may make the GPT-5.4 Thinking appear to have a larger context window (256k) than previous versions. However, according to the original definition, its actual context window size is no more than the context window of GPT-4 Turbo released in 2024.

Did you know GPT-5.4 Thinking has a 1M token context window in the API, but only 32K in ChatGPT Plus ($20/month) and 128K in Pro ($200/month)?

Recently, OpenAI has also changed the definition of context window. Originally, context window is defined to be the input length only. But now, OpenAI combines the input length and output length together, and calls the combination as the new "context window". This combined length may make the GPT-5.4 Thinking appear to have a larger context window (256k) than previous versions. However, according to the original definition, its actual context window size is no more than the context window of GPT-4 Turbo released in 2024.

If ChatGPT's user interface does not provide a token counter just like what Gemini did to their customers, then the confusion about the context window size remains high. Without the token counter, customers never know how much context token they have used, as if they are always in a dark room. If OpenAI ever cares about the transparency to customers, then the company should provide the token counter! Thank you!

Here is my test for GPT-5.4 Thinking VS GPT-5.1 Thinking. My initial prompt: "Can you make a plot? Before making the plot, you need to collect some data from Internet, including the context window sizes of four frontier model families: Claude, Gemini, GPT, and Grok. Since the context window size can increase if users pay more, to avoid confusion we will restrict the data to the most popular monthly paid plans in the $20–$40 range, such as the $20 ChatGPT Plus plan and $30 SuperGrok, etc. Therefore, data about context windows for Pro plans (e.g., $200/month) should be excluded. From November 2022, when ChatGPT was first launched, until today, many frontier models have been released. The dataset should include the context window size for each frontier model released during this period. The plot should show the release date of these frontier models versus their corresponding context window sizes." Result: The 1st image is created by GPT-5.4 Extended Thinking based on the initial prompt. The image is raw and its first trial. The 2nd image is created by GPT-5.4 Extended Thinking as well, after 5 prompts aiming for refinements. Those prompts instruct GPT-5.4 to relabel Y axis, resolve the problem of the collision between some labels, etc. The 3rd image is created by GPT-5.1 Extended Thinking based on the initial prompt. The image is raw and its first trial. The 4th image is created by GPT-5.1 Extended Thinking as well, after 5 prompts for refinements. My impression: 1) Which model has better data accuracy? My answer: In most cases, it could be a tie. But in my case, I feel that GPT-5.1 is slightly better than GPT-5.4. For example, GPT-5.4 was cautious and said: "I moved the release date of Gemini 2.5 Pro from 2025-03-25 to 2025-06-17 for this consumer-plan chart, because Google announced the model and its 1M context on March 25, but Google says 2.5 Pro became accessible in the Gemini app on June 17. For a chart restricted to mainstream paid consumer plans, June 17 is the better date." But GPT-5.4 still maintained that Grok 3 had 1M context on the $20–$40 consumer tiers, even after I asked it to double-check the accuracy of all data points it had collected based on its graph. It started to doubt the accuracy of that data point only after I specifically asked it: "Are you sure that 1 million context window of Grok 3 is for the monthly plan of $20~$40, not for expensive API only?" And it finally admitted: "1M claimed by xAI; consumer-plan exposure not explicitly documented." In comparison, GPT-5.1 found that "Newer Grok versions can go to 1M tokens via API, but coverage of the SuperGrok subscription suggests the chat product is capped around 128k context." So, my impression about the data accuracy they collected is that it is roughly a tie in most cases. In this particularly case, however, I feel that GPT-5.1 is slightly better. 2) Which model produces clearer graphs? My answer: The presentation skill of GPT-5.4 is better than GPT-5.1. For example, when I asked why the resolution of the PNG graph by the first trial of GPT-5.1 is too low, it replied: "In the last version I saved the figure at about 150 DPI with a ~10×5 in canvas. That’s ~1500×750 px. The ChatGPT UI then downscales the image to fit the chat column, which is why you saw something like 989×491 in the alt text." To get higher resolution, I had to specifically ask it to do: "Figure size: 16 × 8 inches DPI: 320" However, in comparison, GPT-5.4 could create the PNG at the resolution at 2818 X 1513 in the 1st trial. For another example, to solve the collision between some labels, I prompted: "If you are smart enough, they might be a way to avoid the collision of the labels." By just using this prompt, GPT-5.4 could solve the collision better than GPT-5.1, because GPT-5.4 was able to adjust the positions of each label and use line segments to connect the data points to the corresponding labels. That is a great skill for presentation.