Fair point. I don't see it consistently myself, but there are def moments where it just stops parsing context on simple tasks/stops thinking. Not sure if it's model regression, context rot, or just prompts getting…
In what way is it getting worse — the model's reasoning, or your own setup drifting underneath you? My observation: same model, same task, but different CLAUDE.md / hooks / skill state produces dramatically different…
Solo dev in similar situation here. Agree with some of the other comments that the moat is not the code, especially in OSS. I'm trying to find a sweet spot between the OSS part of the software and a potential premium…
Could also be a quiz or a mini lecture. It knows all about the context you are in and the problem you are trying to solve, so might as well learn something. Like many others starting out, I built agents with…
Fair point. I don't see it consistently myself, but there are def moments where it just stops parsing context on simple tasks/stops thinking. Not sure if it's model regression, context rot, or just prompts getting…
In what way is it getting worse — the model's reasoning, or your own setup drifting underneath you? My observation: same model, same task, but different CLAUDE.md / hooks / skill state produces dramatically different…
Solo dev in similar situation here. Agree with some of the other comments that the moat is not the code, especially in OSS. I'm trying to find a sweet spot between the OSS part of the software and a potential premium…
Could also be a quiz or a mini lecture. It knows all about the context you are in and the problem you are trying to solve, so might as well learn something. Like many others starting out, I built agents with…