Viewing profile — formerOpenAI

I’ve been working on a framework called RCC (Recursive Collapse Constraints). It’s not an alignment proposal — it’s an attempt to describe the structural limits of any inference sy…

People usually assume their pain is personal — some mix of bad habits, lack of discipline, or being “wired wrong.” But there’s another possibility: most of what feels like personal…

OP here. A couple folks asked if RCC is “just another alignment/interpretability thing.” That’s not really what I’m trying to do here. Very short version: RCC isn’t saying how mode…

I’ve been playing with LLM failure modes lately (hallucination, planning falling apart after ~10 steps, long-context weirdness). At some point I started wondering: what if these ar…

OP here — adding a bit more color. RCC isn’t a new model or training method. It’s basically a boundary effect you get when a predictor has no access to its own internal state or to…

I’ve been investigating a pattern in LLM failures that didn’t make sense when explained through data quality or model scale. Hallucinations, planning drift after ~8–12 steps, and l…

[dead]