Greg G11

Why are all my sessions logging out and won’t log back in properly going around in circles and then API Error: 529 Overloaded. This is a server-side issue, usually temporary — try again in a moment. If it persists, check status.claude.com. @claudeai @AnthropicAI

@levelsio You're absolutely right

I can't believe we were right Claude was dumbified on March 4, just when we noticed!

@dhruvtwt_ @nvidia I've not seen one work yet have you?

Why is no one talking about this? @nvidia is offering around 80 AI models via hosted APIs absolutely for free. You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc. This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and even with Cursor IDE. Setup: – Grab API key: build.nvidia.com/models – base_url = "integrate.api.nvidia.com/v1" – api_key = "$NVIDIA_API_KEY" – select model (e.g. minimaxai/minimax-m2.7) If you’re building or experimenting, this is basically free inference. Lock in and start building today anon. Thank me later.

I'm mainly on Telegram to talk to my AI agent. It's a shame though about how the channels work and it always defaults to General when you've got lots of topics in a channel. You want to be able to go back to that topic easily but you can't and then I end up typing in the wrong topic “general” As that's what it defaults to when you're moving in and out all the time

We’ve done more than all our competitors combined — yet it’s not nearly enough. We need to do 10–20× more.

Unfortunately it's really buggy. You ask for the URL on the front page before I log in. When I click that, it asks me to sign up; then I sign up and it's forgotten the URL. I've got to put it in again. When it eventually does do the analysis, the page is blank even though I get the email that it's done. When you do click in the email to go to the dashboard, it asks you to log in again, logs you out of your session that you were already in, and then can't log in. There are too many bugs here. Once you eventually get inside, it's not really offering anything until you upgrade to the max plan for $49 min

this is the easiest way to get your first 100 users: > go to okara.ai > drop your product url > it analyzes your site, defines your icp and deploys a team of specialized ai agents that work 24/7 to help you drive traffic and users

@elonmusk When's CLI?

Grok 4.3 is still an early beta that will improve almost every day, but try it out! We will publish release notes as we fix bugs and add functionality.

@TraderDiegoX Interesting are they better than the ones out there

I used Claude to code 2 TradingView indicators that are saving me hours every week. 1. Intraday Key Levels 2. NWOG + ORG + Stats I’m giving both away completely free. Like + Comment “INDICATORS” and I’ll DM them to you. (Must be following)

@HeyGen Is it better than remotion?

We built our launch video in Claude Code using HyperFrames. Now it's yours. Open source, agent-native framework. HTML to MP4. $ npx skills add heygen-com/hyperframes RT + Comment "HyperFrames" to get the full source code of this launch video (must follow)

Cli

Your AI agent can now generate and ship videos. HeyGen CLI is now live. Run one command and your agent handles it all: script → avatar creation → video → delivery All from the terminal. Just your agent and the CLI. RT + Comment “CLI” and we’ll DM API credits (must follow)

@elonmusk But no cli no desktop app. Can’t use it until it has a cli and then let’s see how it performs

Grok

@bridgemindai x.com/om_patel5/stat…

Claude Mythos is not a small upgrade. This is a generational leap. 77.8% on SWE-Bench Pro. Claude Opus 4.6 scores 53.4%. That's a 45% improvement on agentic coding. 82.0% on Terminal-Bench 2.0. Claude Opus 4.6 scores 65.4%. Not even close. Anthropic just showed us why they were willing to rate limit paying customers, cut off OpenClaw, and burn goodwill for weeks. They were saving capacity for this. Claude Mythos in Claude Code is going to be a completely different product. The model I've been building BridgeMind with is about to look like a toy.

Claude on iOS just added the feature I've wanted since day one. Ask it to draft a message, it puts it in a card, tap it and send straight to Telegram, iMessage, email, any app. No more copy pasting AI responses and stripping out headers and waffle. Just the message, ready to send

@AlexFinn So why are you not planning into the kanban? Why does that need an API and then open claw executes whatever is in the kanban? That doesn't require any anthropic integration at

If you used a Claude subscription with OpenClaw, read this: Unfortunately all other AI models out there absolutely suck with OpenClaw compared to Opus It's just a fact and anyone denying this is delusional So here is my new recommended OpenClaw setup: Pay for the Opus API and use it as your orchestrator Then use other models as the execution layer If you do this correctly, yes your costs will go up, but not by as much as you think I use my ChatGPT subscription as the coding execution. GPT 5.4 is excellent at coding. When The Opus orchestrator gives a coding task to the ChatGPT subagent, it always performs really well If you are on the Pro plan, you should have enough usage to have ChatGPT be the execution layer for every task. But if youre on the $20 a month plan, youre going to need other subscriptions to handle other tasks GLM 5.1 and Qwen are excellent. I'd get a cheap sub through them and have them handle all other tasks given to them from the orchestrator The best setup tho if you have the hardware is Opus API for orchestrator, ChatGPT for coding, then local Gemma 4 and local Qwen handling everything else. Right now have Gemma running on my DGX Spark and Qwen 3.5 on my Mac Studio. They handle all other execution from my Opus API orchestrator Unfortunately all options above will cost more than the $200 a month subscription. It just is what it is. But if you optimize correctly it wont cost much more, and you'll still get frontier performance. OpenClaw is the most powerful piece of software ever released. $200 a month ($2,400 a year) was a steal for a digital employee. Honestly anything under $50,000 a year is a no brainer if you run a serious business. The situation isn't great but you also need to face reality: Claude Opus 4.6 is the best model for OpenClaw. If you use any other model, your productivity will suffer Business is a battlefield and I refuse to fall behind, so despite me not being happy with the Anthropic decision the setup above is what I'm going with Virtue signaling might get me brownie points on the internet, but it won't increase my productivity

@bridgemindai All eyes on you mate. This is very interesting what you've done here. I totally agree with everything you've just said. Well done

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.

What you’ve done here is create fear. I don’t use third party tools in a loose way, I work through CLI, code, and desktop, yet this change makes me question where the line is and what could trigger a restriction. There’s well known research showing that when people feel watched or constrained, they become less creative and less willing to explore. That’s exactly the effect this creates. Instead of encouraging deeper use, it makes me hold back. I’ve been through this before, long before AI. An account was flagged incorrectly, it took months to resolve, and by the time it was fixed the damage was already done. That’s the concern. If my account gets restricted, even by mistake, I’m stuck waiting while work stops. It makes me reluctant to invest more time or build anything serious on top of Claude because it feels like control sits entirely on your side.

Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.

@elonmusk If it’s beating opus why no cli so we can use it with packages like anthropic have? Please do this. Sick and tired of anthropic messing us all about

Current release of Grok is much than beta 1, which beat Opus in this arena. We usually update the model twice a week. Try the current version of Grok Heavy and you will be pleasantly surprised.

@noahzweben @bcherny Dispatch is useless to me on mobile… UNTIL I can control and talk to current desktop session. Everyone wants to pick up where they left off and walk out the door and continue the cowork desktop session

You can now set the permission mode for coding tasks in Dispatch. We recommend using Auto mode for the safest and most seamless Dispatch experience but any of your allowed permissions are available. Note if you use Bypass Permissions you need to approve session start.

@bcherny @itsolelehmann I think this would be really good; however, token usage is going to be an issue with you guys due to that. That's what made me start using other agents from different companies

@itsolelehmann We’re always experimenting with new ideas. 90% don’t ship because we don’t think they’re good enough experiences. Still on the fence about this one — should we ship it?

i can't believe more people aren't talking about this part of the claude code leak there's a hidden feature in the source code called KAIROS, and it basically shows you anthropic's endgame KAIROS is an always-on, *proactive* Claude that does things without you asking it to. it runs in the background 24/7 while you work (or sleep) anthropic hasn't turned it on to the public yet, but the code is fully built here's how it works: every few seconds, KAIROS gets a heartbeat. basically a prompt that says "anything worth doing right now?" it looks at what's happening and makes a call: do something, or stay quiet if it acts, it can fix errors in your code, respond to messages, update files, run tasks... basically anything claude code can already do, just without you telling it to but here's what makes KAIROS different from regular claude code: it has (at least) 3 exclusive tools that regular claude code doesn't get: 1. push notifications, so it can reach you on your phone or desktop even when you're not in the terminal 2. file delivery, so it can send you things it created without you asking for them 3. pull request subscriptions, so it can watch your github and react to code changes on its own regular claude code can only talk to you when you talk to it. KAIROS can tap you on the shoulder and it keeps daily logs of everything. > what it noticed > what it decided > what it did append-only, meaning it can't erase its own history (you can read everything) at night it runs something the code literally calls "autoDream." where it consolidates what it learned during the day and reorganizes its memory while you sleep and it persists across sessions. close your laptop friday, open it monday, it's been working the whole time think about what this means in practice: > you're asleep and your website goes down. KAIROS detects it, restarts the server, and sends you a notification. by the time you see it, it's already back up > you get a customer complaint email at 2am. KAIROS reads it, sends the reply, and logs what it did. you wake up and it's already resolved > your stripe subscription page has a typo that's been live for 3 days. KAIROS spots it, fixes it, and logs the change endless use-cases, it's essentially a co-founder who never sleeps the codebase has this fully built and gated behind internal feature flags called PROACTIVE and KAIROS i think this is probably the clearest signal yet for where all ai tools are going. we are heading into the "post-prompting" era where the ai just works for you in the background like an all-knowing teammate who notices and handles everything, before you even think to ask

@_catwu @bcherny Will it use my whole weekly amount of tokens just to run that setup?

We've made setting up claude.ai/code with GitHub much easier! You can now run /web-setup in a local `claude` session to use your local GitHub credentials on the web