There's a contradiction in that list: proper code reviews require knowledge of the problem the code professes to solve. If AI is poor at context-dependent details, it can't shine at reviewing code.
It doesn't say the AI is poor at context dependent details. Specifically it says multi-file context or context dependent on knowledge of multiple domains. There's not necessarily any contradiction here.
SEEKING WORK / Frontend and Full Stack web development / London, UK or remote
A driven and dedicated senior full stack web developer with 15 years professional experience. Worked in NZ / AUS / UK for companies large and small accross a range of industries from Finance, Media, eCommerce and online Marketplaces - leading teams in sprints, and delivering large SaaS projects to market.
Location: UK - London
Remote: Yes, within European timezones
Willing to relocate: No
Technologies: Go, Javascript (Node, React, ES6+), ReasonML, API design, web performance, Full stack dev
Australian here, suspect he's spent significant time in both countries because the way he says 'this' is not how an Australian accent sounds, but other parts of his speech sound very Australian.
I thought it was kiwi too. I've spent more time in NZ than OZ though and am less familiar with the Australian accent. If this website[1] is correct, then the company is registered in NZ at least.
Review code - Shines
Finding bugs - Shines
Suggesting coding patterns you want and suggest to LLM - Shines
Explaining error messages - Shines
Writing code from scratch - Mediocre
Architecting a solution - Mediocre/Poor
Understanding code or solutions it has no clue about - Poor
Contextual multi-file or multi-domain code understanding - poor