Nothing formal or specific to Claude Code. Just ad-hoc reviews of usage charts and off-hand comments that, in the near future, continued employment will require the adoption of AI tools.

Thanks for sharing. I thought I was the only one suffering from the flickering issue and the growing number of user experience bugs. If I weren't required to use AI for work, I would stop using the tool.

The mandated use of GenAI tools at work tends to color our opinions. Many developers are stuck in the huge chasm between the hype-driven expectations of engineering leadership and the far less impressive reality.

I followed a similar journey, trying every tip and trick out there to get my AI coding agent to produce something approaching production quality. Recently, it started adding todos instead of implementing functions or claiming the failing tests weren't related, all while claiming success.

Sometimes? With few exceptions, doesn't the nature of building AI solutions at scale force a dependency on the major models?