wsaadX

@birdabo for that much they could have the best plan and the best server hosted for 20k a month

how is this an achievement? 💀

@bridgemindai hows your experience ? im installing now

Just set up the Hermes Agent on my NVIDIA DGX Spark. It's better than OpenClaw and it's not even close. Self-improving AI agent. It doesn't just execute tasks. It learns from them.

@bridgemindai bro just stick to self hosted im stepping away from claude dependency

The rate limits are back. 100% session usage. Rate limited on Claude Code again during peak hours. $200/month Max plan. Last week Anthropic said they fixed it. Cut off OpenClaw. Gave us a $200 credit. Apologized. It worked over the weekend. Low traffic. Everything felt normal. I told you all it was fixed. It's not fixed. Peak hours on a Tuesday and I'm at 100% with 59% weekly usage. The same pattern we saw before the OpenClaw cutoff. OpenClaw wasn't the problem. Capacity is the problem. Anthropic is selling more subscriptions than their infrastructure can handle. That's it. That's the whole story.

@bridgemindai i honestly quite anthropic ill probably be back when mythos is out, i literally caught opus directive to subagents to create stubs on a prod project

@sad_walli Distilled models are underrated

OpenClaw running on my NVIDIA DGX Spark. No Anthropic servers. No rate limits. No subscription. Claude Code rate limited me. Anthropic cut off OpenClaw from subscription limits. So I bought my own hardware. Now I'm running OpenClaw locally on a Grace Blackwell chip. The same tool Anthropic tried to throttle, running on infrastructure they can't touch.

@heynavtoor Nobody's actually creating an agent that does something different. Everything is just to create more junk nobody's creative. It's just hey I created this agent/ tool it can make you an app and guess what its a TODO list lol

🚨 Claude Code costs $200/month. GitHub Copilot costs $19/month. Jack Dorsey's company built a free alternative. 35,000 GitHub stars. It's called Goose. An open source AI agent built by Block that goes beyond code suggestions. It installs, executes, edits, and tests. With any LLM you choose. Not autocomplete. Not suggestions. A full autonomous agent that takes actions on your computer. No vendor lock-in. No monthly subscription. Bring your own model. Here's what Goose does: → Works with ANY LLM. Claude, GPT, Gemini, Llama, DeepSeek, Ollama. Your choice. → Reads and understands your entire codebase → Writes, edits, and refactors code across multiple files → Runs shell commands and installs dependencies → Executes and debugs your code automatically → Extensible through MCP. Connect it to any external tool. → Desktop app, CLI, and web interface. Pick your workflow. → Written in Rust. Fast. Lightweight. No bloat. Here's the wildest part: Block is a $40 billion company. They built Cash App, Square, and TIDAL. They use Goose internally. Then they open sourced the entire thing. This isn't a side project from a random developer. This is production-grade tooling from a company that processes billions in payments. Built for their own engineers. Given to everyone. Claude Code: $200/month. Locked to Claude. GitHub Copilot: $19/month. Locked to GitHub. Cursor: $20/month. Locked to their editor. Goose: Free. Any LLM. Any editor. Any workflow. Forever. 35.3K GitHub stars. 3.3K forks. 4,078 commits. Built by Block. 100% Open Source. Apache 2.0 License.

@luongnv89 @MEEcom44 it genuinely works good im on qwen3.52b

@MEEcom44 i am using qwen in claude code. if u meant comparing to claude models, then it can be around haiku level

> 2h30 running > 11 tasks completed > 55k tokens consumed pretty clean work done by qwen3-coder-next local/self-host AI Coding tools are pretty good > no usage limit > privacy > still get the job done the project is live at: github.com/luongnv89/slee…

@bridgemindai lol and i got A6000 plan on thunder

Claude Code rate limited me so hard I bought a $5,000 NVIDIA DGX Spark. Arriving tomorrow. A personal AI supercomputer. Anthropic cut off OpenClaw users. Slashed Claude Opus 4.6 rate limits. Told $200/month Max plan customers to use less. Then gave us a credit as an apology. This is what happens when AI companies have too much power over your workflow. One update and your entire stack breaks. Local models are the only infrastructure no one can throttle. No rate limits. No 529 errors. No surprise policy changes. Tomorrow I'm testing the DGX Spark live on stream. Running local models through real vibe coding workflows. The goal is simple. Never depend on a single provider again.

@rezoundous lucky you me the same 5 prompt

So I've tried about 5 prompts doing minor updates for my project in Claude Code, and the usage limits are much better. It is still not as good as it was in beginning of March, but miles better than this past week. Try it out and see if that's the case for you guys as well.

@carazy @code_kartik @claudeai lol no man I use opus as orchestrated. Everything is sub agent. He only reviews, but there is this bug. I don't know if it's touching everybody but look at. Tell me if that's possible to be locked out for four hours every five hours and still hit the weekly limit on 5X max plan

@sad_walli @code_kartik @claudeai I literally spent 12 hours in 4 sessions yesterday multitasking with the 100 plan and no issues. I really wonder how people are using it when this doesn't seem remotely possible to me. Do you guys just turn opus on high and say like solve cancer or something?

New in Claude Code: auto mode. Instead of approving every file write and bash command, or skipping permissions entirely, auto mode lets Claude make permission decisions on your behalf. Safeguards check each action before it runs.

@drfunk555 @bridgemindai I'm on Max 5X and I haven't managed to do this. That fucking session is out of control. I make three prompts read two files of 400 lines. The session is done within 15 to 20 minutes. Locked out of five hours. The good news is that they gave me $85 in usage because of this

@sad_walli @bridgemindai How did you manage this? What $$$ plan are you on?

The truth is finally out. Anthropic just emailed every Claude subscriber. The rate limits weren't a bug. Third party tools like OpenClaw were putting "outsized strain" on their systems. Anthropic's fix? Cut them off. Starting April 4, third-party harnesses no longer get your subscription limits. Pay-as-you-go only. To make up for it, every subscriber gets a one time credit equal to their monthly subscription. I'm getting $200 in extra usage. This is huge. If this is what was killing Claude Code rate limits for Max plan users, tomorrow should feel like a completely different product. I'll be testing Claude Opus 4.6 all day and reporting back. Stay tuned.

@LLMJunky guys you need to voice yourself @AnthropicAI made the right thing

I did it. Found a way to greatly reduce usage rates in Claude. step 1: navigate to your .claude folder and open settings.json make the following changes: json { "model": "claude-sonnet-4-5", "compactThreshold": 200000, "subagentModel": "claude-haiku-4-5-20251001" } save and close the file step 2: back in your terminal, run claude to open a new session - once you're inside, type `/effort medium` - press enter to save step 3: now let's make sure we're not using unnecessary additional tokens in outputs. type /config scroll down to "verbose output" press space bar and set to "false" step 4: good. now for the most important step press ctrl+c once to pause the session you'll see a prompt asking if you want to exit, press ctrl+c again to confirm keep your terminal open step 5: type the following: `npm i -g @openai/codex && codex`

@lydiahallie this is just mocking... if not stealing from their customers at this point

Thank you to everyone who spent time sending us feedback and reports. We've investigated and we're sorry this has been a bad experience. Here's what we found:

@Darkstormeuhhh @claudeai its just crazy got timed out after 15 min every 5h and the whole week was gone i mean the 3 days

@sad_walli @claudeai whoa did you just used that in like 3 days ? They have to be joking that's ridiculous

Microsoft 365 connectors are now available on every Claude plan. Connect Outlook, OneDrive, and SharePoint to bring your email, docs, and files into the conversation. Get started here: claude.ai/customize/conn…

@TruthAmmo @claudeai same did it today, this is getting out of hand its been 2 weeks like this 15/30 min of work for 4h30 of pause and the meter is still on

@sad_walli @claudeai i cancelled, this is ridiculous

@ersinkoc im piggy backing on this horrible 4 days week

I didn’t do anything heavy or write much code, yet after just one-third of a 5-hour session, 5% of my weekly limit was already gone. I’m not going to waste time digging through .claude logs to calculate exact token usage and analyze this mess but it’s clearly not high usage. I’m on the 20x Max plan, and these aren’t even peak hours. At this rate (~15% per session), are we seriously not going to be able to run even 7 sessions in 7 days? @claudeai @AnthropicAI @bcherny @lydiahallie

@theo @AnthropicAI @claudeai i guess we need to talk about it it

We need to talk about the Claude Code rate limits