>TLDR: Greg Kroah-Hartman says that last month something magical happened and AI output is no longer "slop".

Opus 4.6 has been a step change. It's simply never wrong anymore. You may need to continue giving it further clarification as to what you want, but it never makes mistakes with what it intends to do now.

▲

Balinares 4 hours ago | parent | next [-]

Yo, just because you can't tell when Claude is wrong, doesn't mean it's right.

I do agree that the Q1 2026 models in general have passed a threshold, but goodness almighty Opus 4.6 still screws up a lot.

	▲	no_shadowban_6 4 hours ago \| parent [-]
		> Yo, just because you can't tell when Claude is wrong, doesn't mean it's right. Just because you can't tell when Claude is right, doesn't mean that you are. This shit is AGI, with decades + billions of dollars of research and development behind it. So don't get all high and mighty now, acting like you know better than Claude.

▲

binarymax 5 hours ago | parent | prev | next [-]

It’s wrong. It made large mistakes on my code literally yesterday.

▲

brcmthrowaway 5 hours ago | parent [-]

Wrong context

	▲	banannaise 3 hours ago \| parent \| next [-]
		Ah, the eternal handwave for anything the AI doesn't do well - it must be user error.
	▲	binarymax 4 hours ago \| parent \| prev \| next [-]
		No. Aside from just making an algorithm that didn’t even run, it refused to use an MCP that it had registered in the same context session.
	▲	9864247888754 4 hours ago \| parent \| prev [-]
		[dead]

▲

taormina 3 hours ago | parent | prev [-]

Can I get your magical version of Opus that works? 4.6 has been a side grade at best, and worse than prior models most days.