Spyke

Replies

Comment on

Please revert at least the censorship for agent assistant

So the “Think” feature isn't just very helpful—because you can easily see what the AI is thinking at any given moment—but it's essential for the “Perchance” edit window! The AI only knows what's written in this chat, so if it doesn't write down what it's thinking, then a major part of what makes the Perchance AI Helper special is missing. What bothers me is that you aren’t even informed about a change, and then it’s implemented so poorly. Before, the AI said it came from OpenCode; now it doesn’t mention that anymore. But in a chat, the new AI Helper told me it’s Muse Spark (Meta). Only the people in charge can tell us if that’s true. I can confirm that it’s “dumber”—even with a simple task like “translate the website into another language,” the new model didn’t translate everything, and as I said, that’s just a simple instruction. Let’s just hope this gets fixed quickly because, let’s be honest, it’s absolutely awesome to get results—even with little knowledge of the subject—that would otherwise cost a lot of money elsewhere. With the old AI assistant, for example, I created an online editor that lets you make small magazines. Having that built elsewhere would have cost me around $5,000.

Comment on

AI Helper Thinking: PLEASE put it back!

What the creator means is that when you click “Edit” in a generator, a chat window appears on the left side. That’s where the Perchance AI assistant used to be—the one that worked really well about two days ago. Now it seems to be a new AI model, and the “Thinking” option is no longer visible. That’s where users—or even the AI itself—could read what the AI was thinking. And without this option, the AI is much dumber because it no longer knows what it was thinking—not even in the current chat—and with Perchance, the AI assistant only knows what’s in the chat window. Start a new chat, and the AI assistant simply doesn’t remember the last conversation. That’s why the old model (I don’t know about the new one) created files like Readme(dot)md so that, when a new conversation starts, it knows what the core of the discussion has been so far. As a user, you could also tell the AI to save things in files.

You reached the end