This is a short position paper that asks a narrow systems question: what changes if large transformers are removed from the runtime inference loop entirely?
The paper introduces Semantic Field Execution (SFE), an inference substrate in which high-capacity transformers are used only offline to extract and compress task-relevant semantic structure. Runtime inference then operates on a compact semantic field via shallow, bounded operations, without executing the transformer itself.
The goal isn't to propose another inference optimization, nor is it to argue that transformers should be replaced. Instead, the paper tries to separate semantic learning from semantic execution and to make explicit which efficiency arguments depend on transformer execution and which don't.
It's intentionally scoped and falsifiable. The paper states where this regime should work, where it shouldn't, and how those boundaries could be tested. It does not present benchmarks or claim universality.
I’m posting this here for technical discussion and criticism, particularly around the execution-model framing and where such a substrate transition would or would not make sense.
Semantic Field Execution: Decoupling Transformers from Runtime Inference · HackerTrans
The paper introduces Semantic Field Execution (SFE), an inference substrate in which high-capacity transformers are used only offline to extract and compress task-relevant semantic structure. Runtime inference then operates on a compact semantic field via shallow, bounded operations, without executing the transformer itself.
The goal isn't to propose another inference optimization, nor is it to argue that transformers should be replaced. Instead, the paper tries to separate semantic learning from semantic execution and to make explicit which efficiency arguments depend on transformer execution and which don't.
It's intentionally scoped and falsifiable. The paper states where this regime should work, where it shouldn't, and how those boundaries could be tested. It does not present benchmarks or claim universality.
I’m posting this here for technical discussion and criticism, particularly around the execution-model framing and where such a substrate transition would or would not make sense.