[pxc]

For programming, at least, there are also problems with overall output quality, instruction following, and the scopes of changes.

LLMs don't do well at following style instructions, and existing memory systems aren't adequate for "remembering" my style preferences.

When you ask for one change, you often get loads of other changes alongside it. Transformers suck at targeted edits.

The hallucination problem and the sycophancy/suggestibility problem (which perhaps both play into the phenomenon of being "confidently wrong") are both real and serious. But they hardly form a singular bottleneck for the usefulness of LLMs.