Exception418

@dpratyush02 It depends on what you did in that hour. Up until a month ago, I was also on the Pro plan and using Sonnet, I never hit the limit. Now I have the Max plan using Opus, and I never hit the limit. I use Claude daily for my work.

Yesterday I purchased the Claude Code $20 subscription. Within 1 hour, it showed this message. Why is Claude showing this only to me? I really feel more regret purchasing premium

@ivanburazin Just use the freaking api

Anthropic is selling it as a claude subscription, then charging a premium to actually run the agent framework that's all the rage atm. You can’t brand it as a comprehensive subscription only to pull the rug on its core utility. From a consumer pov, the default mental model is to assume the "claude subscription" provides unrestricted access to anthropic's models. Hooking up openclaw is naturally the next step. No one hates a company for having tiered pricing for different services based on usage patterns. Claude subs are subsidized for individual use. Third-party harnesses create outsized strain on their systems. If you're running openclaw 24/7 with agents executing tasks nonstop, you can just pay the api costs for the actual compute you're burning. But the branding should have been clearly distinct - subscriptions cover products like claude code and cowork, and third-party tools require extra capacity, which is billed separately.

@mattpocockuk @0xNomad_ You are just looking for a loophole

@0xNomad_ I don't consider this 'clarity'

I don't know what the fuss is about. Anthropic's rules on using subscriptions are very simple: Claude Code = OK Claude's online platform = OK Agent SDK running in personal software = OK... ish? Agent SDK running in commercial software = NOT OK Claude Code running in CI = ?? Oh, maybe it's not so simple... Agent SDK running in CI = ?? claude -p running in CI = ?? claude -p running in personal software = OK claude -p running on open source software, but run on my personal computer = ?? claude -p running on distributed sandboxes, kicked off by me = ?? Distributing open source software which relies on claude -p, and documenting how to use your subscription with it = ?? A thousand other edge cases = ?? Let me be clear. I have never before experienced, from any developer tool, such a frustrating lack of clarity over the basic terms of usage. I personally asked, 3 weeks ago, and have received nothing but delays. The recent @bcherny announcement did absolutely nothing to clarify things. I say this as someone who just released a Claude Code course - my incentives all align with supporting Anthropic.

@jumperz @agentic_joe What is stopping you from using the competition?

@agentic_joe hmm why would i pay extra when the competition gives you the same thing with actual transparency?

let me get this straight: >you sell a model >someone builds real infrastructure on it >it works so well you can’t handle the load >so you email your entire user base blaming the builder >then offer him the door you didn’t just lose a power user, you just told every dev watching that if they build too hard on claude they’re getting kicked out… aws would never hit up their biggest customer like “hey bro you’re using too much aws lol” but anthropic just did and threw in a coupon..

@xai Yeah i dont even follow this page lol stop giving me notifications

Introducing Quality mode on Grok Imagine – powered by our most advanced image generation model. Quality mode gives you enhanced details, stronger text rendering, and higher levels of creative control. Now available on web and mobile. Try it at grok.com/imagine

@trq212 @alistaiir This is cool. Would be nice if at some point the buddy stats would represent how you use claude.

cant believe I got a SNAIL @alistaiir pls

/buddy

@m1chae1_b @PaulAdams @elonmusk Does it matter how long the conversation is? The AI should not respond like that under any circumstances.

@PaulAdams @elonmusk Bro thought we didn’t see how long his conversation was before he managed to get Grok to say he wants it to say 😆

Troubling

Let claude code spawn a sub agent to plan. If you really want to be dave let another sub agent validate that plan and once approved claude code implements it. After implementation claude code spawns another sub agent to review the code. I am trying this now and the results are pretty decent. Havent used this flow a lot yet to say if this is the way but just letting claude code do everything is definitly not the way

i’m currently testing Opus 4.6 in Claude Code after using Codex for 3 months straight both have a big downside and i’m currently weighing which one actually slows me down more: Codex - random abstractions, random helpers, not that good at frontend, variable/function naming could use some help Claude - less thorough so it often misses places when implementing features, and produces slightly more bugs in general

Guys!!!!🔥🔥 I got a response from @JoeyMoose If I’m able to get 20k likes 😭, I’d get a laptop for school🥲 Please like, repost and tag people. I need everyone’s help 🙏🏽 😪

@manualitica @nick_archuletas @BentoBoiNFT Claude can use your browser and perform any task

@nick_archuletas @BentoBoiNFT Yes it can but can it really? Give it a try and ask it to use your browser….

Why would anyone choose OpenClaw vs Claude Code? Claude now has: • Discord/Telegram integration • Cron Jobs (/loop) • 1M token memory • Webhooks to phone • Can run 24/7 on any Computer or Mac Mini This covers 95% of what people actually use OpenClaw for with better security and easier setup The only reason to stick with OpenClaw is if you want a multi-agent setup. That's the only difference I could think of Going to stick with OpenClaw for now because of this, but the gap is almost at zero

@yashwanth2207 @mreiffy The browser plugin is op. It does burn tokens faster (could be just my imagination) but it gets the job done

@mreiffy so it just... navigated your dashboard on its own? that's a whole different level than just writing code

Claude is getting out of hand. Was building an app with Claude Code and hit a persistent Supabase issue. Asked Claude if it could use the Chrome extension to fix it. Switch tabs… and boom. It was in my Supabase dashboard. Clicking through pages. Debugging. No scripts. No guidance. Just doing the work. We’re not “using tools” anymore. The tools are using themselves 😳

@navarro_ivar @bcgame Loool yeah deserved. What goes around comes around.

I just heard that @bcgame was exploited for over $4,000,000. I guess what goes around really does come around. To the hacker, and I think I speak for all the people who are aware of BCGame’s shady practices… thank you. Drinks on us.

@prudentgambles lets fcking goooo congrats bro

Have you ever seen a max win on a feature spin on Le Fisherman?! EXACTLY, wait for it!

@PeteHegseth @AnthropicAI @DarioAmodei @POTUS "We dont need it, we don't want" but yall doing all of this because they said no lol

Thank you for your attention to this matter. cc: @AnthropicAI @DarioAmodei

@KobeissiLetter Lets hope Anthropic sticks to their values.

BREAKING: The US Pentagon has made a "final offer" to Anthropic seeking unrestricted military use of its AI capabilities ahead of a Friday deadline. Details include: 1. Pete Hegseth threatening to label Anthropic as a "supply chain risk" 2. Anthropic is resisting use of its AI capabilities to surveil Americans 3. Anthropic is resisting use of its AI capabilities for lethal military missions 4. Anthropic was recently awarded a $200 million government contract 5. Anthropic now has just over 24 hours to respond This is a pivotal moment for AI warfare and surveillance.

@TheAhmadOsman Nope

CANCEL your Claude subscriptions Anthropic does not deserve your money Alternatives? - Codex - MiniMax M2.5 - GLM 5 - Kimi K2.5 Hit them where it matters, less money and less data

10x$50 waiting for YOU! Like 💚 RT 🔄 & drop your GamdomID 👇 If we hit 1,000 likes in 24h, prizes DOUBLE! *KYC Lvl 2 verified Gamdom users only.

@crashoverride @kick Yeah haha guy posted in my chat today. Crazy how those accounts have the verification badge though

I shouldn't even have to make this post, but whiz_twitter on Kick is not me. I only go by 'whiz'. The account has since been removed from @kick W @kick for taking action immediately.

@luckybyte1107 Did you withdraw straight to binance? Always put your personal wallet in between.

I want to cry

@tivuhhhh tf did i do lol?

i hate streamers who's profile is all gambling stuff like wheres the personality