It's worth noting that LLMs have been part of the tech zeitgeist for over two years and have had a pretty limited impact on hireability for roles, despite what people like the Klarna CEO are saying. Personally, I'm betting on two things:
* The upward bound of compute/performance gains as we continue to iterate on LLMs. It simply isn't going to be feasible for a lot of engineers and businesses to run/train their own LLMs. This means an inherent reliance on cloud services to bridge the gap (something MS is clearly betting on), and engineers to build/maintain the integration from these services to whatever business logic their customers are buying.
* Skilled knowledge workers continuing to be in-demand, even factoring in automation and new-grad numbers. Collectively, we've built a better hammer; it still takes someone experienced enough to know where to drive the nail. These tools WILL empower the top N% of engineers to be more productive, which is why it will be more important than ever to know _how_ to build things that drive business value, rather than just how to churn through JIRA tickets or turn a pretty Figma design into React.
* The upward bound of compute/performance gains as we continue to iterate on LLMs. It simply isn't going to be feasible for a lot of engineers and businesses to run/train their own LLMs. This means an inherent reliance on cloud services to bridge the gap (something MS is clearly betting on), and engineers to build/maintain the integration from these services to whatever business logic their customers are buying.
* Skilled knowledge workers continuing to be in-demand, even factoring in automation and new-grad numbers. Collectively, we've built a better hammer; it still takes someone experienced enough to know where to drive the nail. These tools WILL empower the top N% of engineers to be more productive, which is why it will be more important than ever to know _how_ to build things that drive business value, rather than just how to churn through JIRA tickets or turn a pretty Figma design into React.