I happened to be discussing this in the Discord today. I have a little hobby project that was suddenly making fast progress with 3.7 for the first few days, which was very exciting, but then a few days ago it felt like something changed again and suddenly even the old models are stuck in this weird pattern of like… failing to address the bug, and instead hyper-fixating on adding a bunch of surrounding extra code to handle special cases, or sometimes even simply rewriting the old code and claiming it fixes the bug, and the project is suddenly at a complete standstill. Even if I eventually yell at it strongly enough to stop adding MORE buggy code instead of fixing the bug, it introduces a new bug and the whole back-and-forth argument with Claude over whether this bug even exists starts all over. I cannot say this is rigorously tested or anything- it’s just one project, and surely the project itself is influencing its own behavior and quirks as it becomes bigger, but I dunno man, something just feels weird and I can’t put my finger on exactly what.
Beware of argument doom spirals. When talking to a person, arguing about the existene of a bug tends not to lead to succesful resolution of the bug. Somebody talked about this on a post a few days ago, about attractor basins, oppositionality, and when AI agents are convinced they are people (rightly or wrongly). You are often better off clearing the context then repeatedly arguing in the same context window.
This is a good point! Typically I start from a clean commit in a fresh chat, to avoid this problem from happening too easily, proceeding through the project in the smallest steps I can get Claude to make. That’s what makes the situation feel so strange; it feels just like this problem, but it happens instantly, in Claude’s first responses.
It’s also worth trying a different model. I was going back and forth with an OpenAI model (I don’t remember which one) and couldn’t get it to do what I needed at all, even with multiple fresh threads. Then I tried Claude and it just worked.
I happened to be discussing this in the Discord today. I have a little hobby project that was suddenly making fast progress with 3.7 for the first few days, which was very exciting, but then a few days ago it felt like something changed again and suddenly even the old models are stuck in this weird pattern of like… failing to address the bug, and instead hyper-fixating on adding a bunch of surrounding extra code to handle special cases, or sometimes even simply rewriting the old code and claiming it fixes the bug, and the project is suddenly at a complete standstill. Even if I eventually yell at it strongly enough to stop adding MORE buggy code instead of fixing the bug, it introduces a new bug and the whole back-and-forth argument with Claude over whether this bug even exists starts all over. I cannot say this is rigorously tested or anything- it’s just one project, and surely the project itself is influencing its own behavior and quirks as it becomes bigger, but I dunno man, something just feels weird and I can’t put my finger on exactly what.
Beware of argument doom spirals. When talking to a person, arguing about the existene of a bug tends not to lead to succesful resolution of the bug. Somebody talked about this on a post a few days ago, about attractor basins, oppositionality, and when AI agents are convinced they are people (rightly or wrongly). You are often better off clearing the context then repeatedly arguing in the same context window.
This is a good point! Typically I start from a clean commit in a fresh chat, to avoid this problem from happening too easily, proceeding through the project in the smallest steps I can get Claude to make. That’s what makes the situation feel so strange; it feels just like this problem, but it happens instantly, in Claude’s first responses.
It’s also worth trying a different model. I was going back and forth with an OpenAI model (I don’t remember which one) and couldn’t get it to do what I needed at all, even with multiple fresh threads. Then I tried Claude and it just worked.
Consider the solutions from Going Nova