We sure did. It's a great writer, better in a harness, will process lots large context, but complex reasoning with convoluted rules and low hallucination tolerance? That's still larger model territory.

▲

ernsheong 5 hours ago | parent [-]

There's still 3.1 Pro though, as ancient as it sounds now

	▲	waldrews 5 hours ago \| parent [-]
		Yup. The problem is that it's bizarrely still not in General Availability status.