As a result, users will keep reusing the same coding or chat session again and again. While it would be better to start fresh for unrelated tasks.
Claude Opus 4.7 has a very large context compared to itself, but IME it is the worst at following instructions, and completely disregards the (small) preferences prompt, even in the first or second message, even if the messages are just a few characters long.
IMO this is entirely a training problem.
It disregards things like “no follow up questions”.
Haiku, for example doesn’t.
This bias is a very human thing, actually now that I think about it. You just disregarded the “even if the messages are just a few characters long”. :)
funny though it is a case in point: language is hard. and i get to hide behind being "preoccupied" . i wonder if llms have their own sense of preoccupation hmmm.
Also reminds me of the gremlin issue with GPT. An (internal) prompt saying "don't say gremlins" wasn't enough.
I've had many long-running sessions and it doesn't suffer the same retardation (the act of delaying, slowing down, or hindering progress) that Opus does.
The quality stays consistent and it actually seems to follow the instructions, todos, etc. even after multiple compactions.
We get how it works. It's just irritating.
I usually work with sessions <300k tokens, Opus 4.7 xhigh, and it simply has holes in it's world model, or some strong conditioning here and there, and it sips through regardless of how strong you will say things and how explicit the rules in system prompt will be.
Even with a fresh session, if you bump into one of these things, it will lead you into circles that will be very hard to break out of. And swearing helps a bit.