HN user
I don't think Google has given up; rather, I believe they are taking a wait-and-see approach and carefully controlling their investment. Furthermore, I feel Gemini is still excellent at simple, short-term, and even multimodal tasks, but it is not well-suited for long-term planning scenarios for AI agents.
I don't really think so. When writing code with AI, I feel like we're doing two different jobs at once: writing documentation and writing code. Even though they're technically two sides of the same coin, it gets really frustrating.
Besides, no matter how good our design docs are, AI just can't grasp the business context outside of what's written. Plus, AI loves to modify things using band-aid patches, making it incredibly hard to keep the code clean. The design logic often gets messy, and you ultimately lose true logical consistency.
My current workaround is to provide detailed architecture and design principles upfront, and also add comments at the top of each file to clearly define its scope. That seems to help a bit.
But my biggest headache right now is that AI struggles to adapt to the latest APIs—it actually likes to revert the new APIs I've just updated back to the older, deprecated ones.
It's such a pity about Philae. With just a little more luck, we could have gathered much more information about the comet, even though its achievements are already truly memorable. I wonder when we'll finally be able to land on a comet again.