[SatvikBeri]

I've never actually run into the issues that people talk about online, like Claude suddenly getting dumb or running out of usage. So there's just not a lot of incentive for me to shop around. I've used Amp a bit, and it's quite nice, but a bit more expensive without the subsidized subscription.

[raincole]

It has always been like this. We actually know that the model performance has been mostly steady[0], but you cannot beat the notion of "evil companies secretly serving us worse models." The meme value is too strong.

[0]: https://marginlab.ai/trackers/claude-code/

[QuantumGood]

Your data support actual strength shifts, not narrative manipulation:

Range of 48-73.5 (peak 53.1+% higher than trough) with a single day shift of ~30%.

You suggest people are usually influenced more by narrative than data, but provide a narrative-heavy, data-light comment, e.g. "always" "know" "mostly steady" (hazy terms for data) "cannot beat" "evil companies" "meme strong".

A followup defining "mostly" and "steady" more clearly, and your purpose in writing in a narrative-shaping style would be helpful.

[mnicky]

Hmm, today's pass rate raised to 73% - interesting, are they AB-testing some new model? This is too high for Opus 4.7.

[gardnr]

Are you using Opus? Sonnet remains as useful as it was while Opus efficacy and token burn rate has soured over the last 4 months.

[fny]

I'm using Opus on xhigh 10+ hours a day, and I've only reached 80% of weekly limits when doing massive ports or refactors. I haven't once hit hourly limits, and I've used Claude very, very aggressively. I guess its a pain point for power users.

[josephg]

I sometimes run multiple claudes at the same time, with each terminal working on a different task. I have 2 going right now.

Its very easy to burn through your quota if you work like that. Especially on high / xhigh.

[plufz]

I used to be mostly at high/xhigh but now at medium I think it actually performs quite well both on results and token usage.

[SatvikBeri]

Yes, I've pretty much used Opus exclusively for the last year, except for a brief period when Sonnet was ahead

[mbreese]

When do you use it the most? I’ve noticed that it most often starts to degrade during 10-5 US East coast time. Late at night, I have the least amount of issues, but without fail, if I’m trying to do anything complex during the day, Claude gets loopy.

[SatvikBeri]

9-5 Pacific Time

[dboreham]

Same here. Works every time. Never ran into usage limits either.