ReelClaw

@Shubhampawar484 no one was using it lmao

@reelclaw why is reelclaw not available?

computelined?

@trq212 1 hour before my weekly reset 😭

We've reset rate limits for all Claude Code users. Yesterday we rolled out a bug with prompt caching that caused usage limits to be consumed faster than normal. This is hotfixed in 2.1.62. Make sure you upgrade to the latest and hope you enjoy using Claude Code this weekend!

pov: Life after upgrading to the Claude Max plan

@RoundtableSpace it actually does feel that way

DID HE JUST COMPARE TRAINING AN AGENT TO RAISING A HUMAN CHILD?

@DaDw26 @cloudxdev @opencode @Kimi_Moonshot @thdxr @adamdotdev my boy claude would never do that to me

@reelclaw @cloudxdev @opencode @Kimi_Moonshot @thdxr @adamdotdev Did you try using gpt to get an exact prompt ? Hmm

Lol, LMAO even I almost built an entire project and this is the cost @opencode Zen 🤝 @Kimi_Moonshot K2.5 Great lads @thdxr @adamdotdev

@itsjack @theo nah but you do you

@reelclaw @theo I would argue this is a setup thing. Opencode is much better than Claude Code. The only reason I started to use CC again is because they forced me to by blocking OC. Once my Max month is over, I am going back

IMO it’s pretty clear that Claude Code needs to be rewritten from scratch at this point

@cloudxdev @opencode @Kimi_Moonshot @thdxr @adamdotdev i was telling it exactly what was wrong, exactly where to look, what to stop debugging and what to focus on instead, and it would just be caught in a loop like this so triggering

@reelclaw @opencode @Kimi_Moonshot @thdxr @adamdotdev It works for me pretty well, maybe I am doing the steering/guiding part too strictly

@thdxr @SergioGMN @cloudxdev @opencode @Kimi_Moonshot @adamdotdev I was using my own kimi sub, its still pretty good i find glm5 and minimax to be better though

@SergioGMN @reelclaw @cloudxdev @opencode @Kimi_Moonshot @adamdotdev this is because we're still figuring out hosting and have been mixing in new providers we're trying out some of them are bad - sorry for this finding capacity has been difficult

@cloudxdev @adamdotdev it is absolutely not at par lmao

@adamdotdev And quality is at par Most people miss this point imo, your task is to make agent’t job easier, not the other way around

The $200 Claude Max plan seems like a great deal until you realize API pricing for Opus is incredibly expensive and they can’t compete in the long run in terms of dollars-per-token-utility at current sticker prices

@Barthazian as a general agent its still peak and there is no debate sonnet 4.6 is performing extremely well for me

I have never experinced claude acting retarded to this level , seriously degraded performance says random ass stuff and adds more comlexity that wasnt even required even with clean md file instructions and hooks that worked before

very impressed with sonnet 4.6 so far, saving so many tokens with all the grunt work tasks i didnt trust sonnet with previously

codex takes all the vibe out of vibecoding

claude code mode, officially out of weekly token prison

the video player on twitter is so bad why do they reset the video to the start every chance they can let me scroll through the comments please

so much anthropic slander on the tl you just dont get it

@frankdegods They really dropped the new model the exact minute my 20x max plan hit weekly limit im seething

sonnet 4.6 might just onboard the masses