> If it stays at arm's length, and if it can "read only", then I am OK with it and actually somewhat pleased with it.
This isn't actually about AI. it's just classic human psychology.
You’ve had a rock-solid workflow for 25 years, so it makes total sense to be cautious and reject features you don't need.
Right now, keeping it at "arm's length" and "read-only" feels safe. But that's usually just phase one. Once that initial trust is established, those boundaries naturally start to melt away. Give it a couple of tax seasons, and you’ll probably find yourself wanting it to take on more of the heavy lifting.
What a time. I am back here genuinely wishing for OpenAI to release a great model, because without stiff competition, it feels like Anthropic has completely lost its mind.
I've used Kimi K2.5 when I run out of Codex quota. It does small and medium things OK. But if I work on complex things, I'll later have to spend two days cleaning up the mess with Codex. Hopefully 2.6 does better.
reply