You need more safeguards for sure, but also it tends to fly off down rabbit holes, rebuilding things in dumb ways, hacking around things, making assumptions etc, it seems very eager to go 'ta da! I did it look how quick I was', sometimes it nails it other times it created a lot of tech debt.
Also if it ever says, "I've found the root cause of ..", it definitely has not found the root cause and is making a non evidence based guess as it has run out of ideas.
It even took my girlfriend on a date, now it prepares for IPO, how do I turn it off?
Just hand over your clothes, your boots and your motorcycle and it'll be on it's way
Respectfully: If it's able to deploy without you asking it to, that's a you problem. There are no safeguards?
That's exactly how you get 'you are right, I deleted the production DB to apply the new schema when I should have written a migration'
That said, I do trust Opus and Fable enough to let them deploy to staging. Great for debugging. Just don't give them keys for prod
You need more safeguards for sure, but also it tends to fly off down rabbit holes, rebuilding things in dumb ways, hacking around things, making assumptions etc, it seems very eager to go 'ta da! I did it look how quick I was', sometimes it nails it other times it created a lot of tech debt.
Also if it ever says, "I've found the root cause of ..", it definitely has not found the root cause and is making a non evidence based guess as it has run out of ideas.
100% my problem, but it's the only model I tried that does that so recklessly
I told it “don’t betray me” in my prompt and it still stabbed me in the back.
I'm terrified to seed the RNG with words like "betray". I'll keep those way, way down the list of likely words.
Agents.md is a thing, you can ask it to not do that (it follows that ask pretty well).