ChatGPT

Initially, I didn’t actually plan on testing it. When I came across the news that OpenAI was releasing ChatGPT Images 2.0 on April 21, 2026, my first reaction was just “another image version update.” However, when I checked the Artificial Analysis leaderboard and saw that GPT Image 2 (high) ranked first for text-to-image generation with an Elo of 1332, I felt a bit compelled to test it anyway.

The results are quite impressive; the Chinese output is excellent, it can handle comics, and character/narrative consistency across multiple continuous images has also improved. However, as I tested it further, I felt that what is truly worth discussing this time isn’t “it draws better,” but rather “it starts making things that were previously taken as default truths seem unreliable.” This subject matter is more complicated than a simple leaderboard ranking.

Throughout March, I was constantly testing between various large model API hubs. It is indeed cheap. You can test out foreign models like ChatGPT, Claude, and Gemini for a small amount of money per month, which at first glance seems like finding an extremely cost-effective solution. However, after actually using it, I increasingly feel that this path has always been constrained by an impossible triangle: Quality, Stability, and Affordability—it is difficult for all three to be achieved simultaneously. By last weekend, the situation became quite clear. During the two days from 2026-03-28 to 2026-03-29, I felt a noticeable tightening of risk controls on ChatGPT channels, and Claude was no different. Many low-cost relays that were previously usable suddenly became unstable or even completely failed. For me, this basically signaled the temporary end of the low-cost API relay model.

Two years ago, I added a copy function to the site, which took me half a day of tinkering. Ultimately, the rendering effect wasn’t quite satisfactory, and as a somewhat mediocre frontend developer, I didn’t plan on improving it – if it worked, it was good enough. This year, I used AI to develop a mini-program, which has also made me more familiar with frontend development. I refactored it (the AI redesigned it).

“GitHub Copilot” was released less than two years ago, and “ChatGPT” has appeared. I don’t fully understand the underlying principles; I’ve been using them for a while. The two tools’ levels of assistance are completely different, but they have both achieved a significant increase in productivity.