Thanks for the read! I too have over 20 years in tech and have been going back and forth with Gemini-cli to gamify some tools for integration testing some Enterprise applications and it’s amazing what can be done with Gemini alongside usage of MCP servers. I am finding positive results if I approach problems in chunks and provide clarity in prompt instructions. The AI will make mistakes and sometimes get caught up in loops for some problems (like application routing.. lol) but I am happy to step in and effectively pair program with the AI when issues are present. I notice too that it has never been a better time to enforce things like how Duplication Is Evil because otherwise the AI may make a change in one area and forget that it has similar changes to make in another file. This applies both to programming logic as well as User eXperience and application behaviour.
Anyway what a world. It would have taken me weeks to create what an AI and myself are able to whip up in a few short, and fun, hours.
Giving a personality to Gemini is also a vital feature to me. I love the portability of the GEMINI.md file so I can bring that personality onto other devices and hand-tailor it to custom specifications.
Local, in my experience, can’t even pull data from an image without hallucinating (Qwen 2.5 VI in that example). Hopefully local/small models keep getting better and devices get better at running bigger ones
It feels like we do it because we can more than because it makes sense- which I am all for! I just wonder if i’m missing some kind of major use case all around me that justifies chaining together a bunch of mac studios or buying a really great graphics card. Tools like exo are cool and the idea of distributed compute is neat but what edge cases truly need it so badly that it’s worth all the effort?