Quote:
Originally Posted by Bill Bumface
You can do this pretty effectively. One agent to code, one agent to PR, one agent to QA. You can prompt the latter two into being incredibly nitpicky. It's getting pretty amazing.
I ran our company trial of Copilot last year and deemed it was really only highly useful for generating boilerplate. We use Go a lot, so that's a pretty good benefit in itself for that language.
3 months ago I built a little Slack bot using a combination of Gemini, ChatGPT and Copilot. It was fairly frustrating how much it screwed up and took me a few days to get it working.
This week I asked Claude to re-write the whole thing and it was utterly flawless and massively improved. It took me about 20 minutes.
I've gone from a mild skeptic to "we're maybe all seriously screwed". I think 90% of the population thought they were screwed when farming machines came out. Factory workers thought they were screwed when robots showed up. Office workers thought they were screwed when computers landed on everyone's desk. We all found new things to move onto, granted with some pain in the transitions.
What worries me here is this is happening so fast and society can't adapt quick enough. It's insane to see this happening.
|
Your experience seems to mirror mine. The half-assed stuff I cobbled together in November now runs pretty much perfectly (for my needs). By and large the biggest hack to get there was to shut up and simplify. My prompts were way too complicated, which tied it in knots. I shifted to a strategy of "here's my problem, go" and suddenly it's lights out.
My concern also mirrors yours... those shifts you mention were huge, there were bumps in the road, and they all happened over about 150 years. We could conceivably have a larger shift than all of them crammed into about 5. I don't know if humans have it in us to adapt fast enough.
I feel there is a legit scenario where we have to just let robo-jesus take the wheel here and help us navigate.