alt Hacker NewsI have Max 5x and use only Claude Opus on xhigh mode. I don't use agents, or even MCPs, and stick to Claude Code.
I find it incredibly difficult to saturate my usage. I'm ending the average week at 30-ish percentage, despite this thing doing an enormous amount of work for (with?) me.
Now I will say that with pro I was constantly hitting the limit -- like comically so, and single requests would push me over 100% for the session and into paying for extra usage -- and max 5x feels like far more than 5x the usage, but who knows. Anthropic is extremely squirrely about things like surge rates, and so on.
I'm super skeptical of the influx of "DAE think Opus sucks now. Let's all move to Codex!" nonsense that has flooded HN. A part of it is the ex-girlfriend thing where people are angry about something and try to force-multiply their disagreement, but some of it legitimately smells like astroturfing. Like OpenAI got done pay $100M for some unknown podcaster and start hiring people to write this stuff online.
Replies
Yea, I never got how people are even able to hit the weekly limits so consistently. Maybe it's because they use it for work? But in that case, you would expect the employer to cover it so idk.
>I'm super skeptical of the influx of "DAE think Opus sucks now. Let's all move to Codex!" nonsense that has flooded HN. A part of it is the ex-girlfriend thing where people are angry about something and try to force-multiply their disagreement, but some of it legitimately smells like astroturfing. Like OpenAI got done pay $100M for some unknown podcaster and start hiring people to write this stuff online.
A lot of people are angry about the whole openclaw situation. They are especially bitter that when they attempted to justify exfiltrating the OAuth token to use for openclaw, nobody agreed with them that they had the right to do so, and sided with Claude that different limits for first-party use is standard. So they create threads like this, and complain about some opaque reason why Anthropic is finished (while still keeping their subscription, of course).
If only OpenAI spent a significant amount of money on some kind of generative software that was predominantly trained on internet comments that'd be able to do all the astroturfing for them...
I was in the same boat until last few days, where just a handful queries were enough to saturate my 5h session in about 30 mins.
Recently I've gotten Qwen 3.6 27b working locally and it's pretty great, but still doesn't match Opus; I've gotten check out that new Deepseek model sometime.