> My own experience w/ 4.6 and 4.7 are that I don't firmly grasp any capabilities improvements over my memory of 4.5, but it's all so fuzzy that it's truly difficult to tell.

I've actually intentionally switched back to 4.5. I hated 4.7 so much that I decided to jump back all the way to 4.5.

Now that I've been using 4.5 for a few weeks, I find it significantly more reliable but a bit more forgetful than 4.6/4.7. I'm okay with that because it's really easy to identify this forgetfulness and nudge it.

I found 4.7's adaptive thinking to be extremely unreliable. It seems to overcorrect on the current message without considering the difficult of the overall problem. I wonder if 4.8 will improve on that.

▲

michaelsalim 42 minutes ago | parent | next [-]

Same here. Went back to 4.5 and was happy I did it. The only frustration was that I can tell the model has declined compared to the first few weeks it was released.

I also recently moved to 4.6 since I started hitting the context limit too often with my current project.

▲

dwaltrip 5 hours ago | parent | prev [-]

If you are using Claude code, just set effort to xhigh.

This one change will probably solve 80% of the problems you have noticed.

▲

whatevaa 2 hours ago | parent | next [-]

Isn't xhigh on opus 4.7 very expensive on tokens?

▲

dwaltrip 2 hours ago | parent [-]

I’ve never ran into the limits on the $100 plan, and rarely even get close.

I normally have only one session going at once though.

	▲	joshstrange an hour ago \| parent [-]
		Same here and while I have multiple sessions going from time to time, my day isn't spent primarily developing software directly anymore (due to role, nothing about LLMs). I only ever hit the $100/mo limits 1-2 times ever and it was always <1hr before reset (once it was <5min, the other was like ~45min). I'm even considering going back down to $20 and using extra usage for the times I need to "burst".

▲

orwin 4 hours ago | parent | prev [-]

This. XHigh and the 'plan' mode for complex tasks is absolutely a must have.

Still, the context window is sometimes too small for my usage.

	▲	jayGlow 2 hours ago \| parent [-]
		agent teams can help with that, the main agent acts as an orchestrator and spawns sub agents to do the actual tasks it generally keeps the main context from overflowing.