I disagree. At least from my experience it still hallucinates a lot of times - it's just better at hiding that. That causes issues and it's hard to believe for me inexperienced person can spot this problems.
It only hallucinates if you use it wrong. Give it enough requirements, context, keep an eye on all it does (like it were a junior developer), and you will get awesome results. AI code assistants are a fantastic tool that can make you 10-100x more productive provided that you know how to use them.
Most of the people saying the kind of things you say don't know how to properly use an AI code assistant.
That's a very lackluster argument. Even if everything you said was true (and to be clear: it absolutely isn't; LLMs will hallucinate no matter what as it's in their very nature), that's still a flaw in the tool. A good tool must not require convoluted dances to make it work halfway decently.
AI code assistants are lazy junior developers (so you need to keep an eye on everything they do, e.g. make sure they don't forget or ignore to do some parts of the work you tell them to do) with the ability to do research as in-depth as a senior developer. Now make your mind about it. When driving an AI code assistant, you must act like you are a softare development manager managing a team of junior developers.
Giving it access to JIRA doesn't make the code it produces more mergable, or reduce the cognitive load and technical debt a massive PR written by AI introduces into complex codebases.