I wonder if it's a harness thing or a model thing at this point. I feel all coding models are quite capable for most tasks I want them to do.

Most of the time I don't need what the bench tests and I'm not really giving them completely ambiguous tasks without any refinement.

I only find marginal differences between models at this point and it almost feels like personality quirks in each model than anything.

▲ BenzeneDream 3 hours ago | parent [-]

When comparing OpenAI and Claude thats pretty much true, but not Gemini... And have you tried Antigravity? Yikes

▲ vrosas 2 hours ago | parent [-]

The CLI version of agy is great. Have you tried it?

▲ taylorfinley 2 hours ago | parent [-]

Do you dangerously allow permissions? I absolutely cannot use it until they ship an auto approver. As it is now I have it write one bash/python script to do everything it wants to, then I review that. Otherwise it is COMPLETELY unusable and it shocks me when I hear people are using it.

	▲	xnx an hour ago \| parent \| next [-]
		Sounds like they shipped some changes today that might reduce approvals: https://x.com/antigravity/status/2100001904969297980
	▲	andai 39 minutes ago \| parent \| prev [-]
		`alias agy="agy --dangerously-skip-permissions"`