t ✰ n y

@JustinPerea @noahzweben @trq212 how are you hitting limit that fast? using agent teams ?

@noahzweben @trq212 I would love to try but I hit my limit until 9am and I'm on the $200/month plan. Idk what to do now for 19 hours 😔

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green. This happens remotely so you can fully walk away and come back to a ready-to-go PR.

@coreyganim yea $500 month retainer.. righttt

the business idea here is staring you in the face: 1. learn this Obsidian + Claude setup 2. offer it as a done-for-you service to consultants, coaches, and creators 3. charge $2-5K per build 4. maintain it monthly for $500/mo retainer most business owners will never set this up themselves. but they'll pay someone who can.

@claudeai can it file a trademark registration or book a flight ?

Available on Pro and Max. Update your desktop app and pair with mobile to try: #dispatch-and-computer-use" target="_blank" rel="nofollow noopener">claude.com/product/cowork…

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

Clawdbot set up has been on my to-dos as i’ve been using Claude / Claude Code.. this is HUGE.

yea i dont know if i wanna open rocket money again

good morning to everyone at @AnthropicAI thank you for empowering dreamers to become doers.

@openclaw @grok explain acp subagents

OpenClaw 2026.3.2 🦞 💬 Telegram live streaming 🔌 ACP subagents on by default 📄 Native PDF tool ✅ openclaw config validate 🇻🇳 Zalo rebuilt in pure JS 🔒 100+ security & stability fixes Sleep is a feature we haven't shipped yet. github.com/openclaw/openc…

@chooseliberty @cathrynlavery Grok is notorious for this. you have to ask it to be detailed in its responses

@cathrynlavery yup I also ran into this. it's common for them to gaslight us. when they create a document you HAVE TO open it and look at it. sometimes they shorthand stuff that should be detailed.

Openclaw tip 🦞 Your agents will lie to you. They'll say "on it!" and not start. They'll say "done!" and it's not done. They'll say "building now" and nothing is running 🤡 Here's what I added to every agent's instructions: Never say 'done' or 'working on it' unless the action has actually started. Every status update must include proof — a process ID, file path, URL, or command output. No proof = didn't happen. A false completion is worse than a delayed honest answer. Now when I'm told something is building, it comes with this:

@Alibaba_Qwen @grok explain in detail for a non technical person to understand. What’s going on here? How can you run models for free.

🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast, great for edge device • 4B → a surprisingly strong multimodal base for lightweight agents • 9B → compact, but already closing the gap with much larger models And yes — we’re also releasing the Base models as well. We hope this better supports research, experimentation, and real-world industrial innovation. Hugging Face: huggingface.co/collections/Qw… ModelScope: modelscope.cn/collections/Qw…

tapping into my genius is ascending me to higher levels

did a demo drive with the @cybertruck and facetimed my girl. told her i traded in my X for the truck. she said she’d be embarrassed getting in and out of the car and everyone she talks to jokes about it. would she feel the same way if i was driving a old broken down corolla. makes a man think

@mrsunday777 @OzanACAR1232643 @perplexity_ai appreciate the tips and insight

easiest structure you can do rn to gain a more consistent session to session transitions is building a bootstrap injection system for your agents. go the extra mile. automate it ... have them boot it at the start of every session. wanna go further ? add a checkpoint system at the end of every session and the start of every session. Have it note all the stuff you were working on or had going on. starts the next session already knowing what was happening on the prior one. takes a process to get right but that should lead you down the right path.

Introducing Perplexity Computer. Computer unifies every current AI capability into one system. It can research, design, code, deploy, and manage any project end-to-end.

@mrsunday777 @OzanACAR1232643 @perplexity_ai Have it log ongoing key details and specifications and updates and then read through the context before all future actions and requests?

@therealtnygp @OzanACAR1232643 @perplexity_ai Build a file-based memory system for your project. Context problem solved. The AI becomes 10x more useful when it can read what you wrote, not guess what you meant.

@mrsunday777 @OzanACAR1232643 @perplexity_ai the biggest challenge for me using the ai tools is context and memory

Probably not, your not wrong Building the infrastructure for your agents to move across devices is what they’re doing. Building the infrastructure for your agents to move across devices while remembering who they are and who you are. And doing it fleet wide simultaneously….. that isn’t what they’re doing… These guys are building you a device agnostic agent. They aren’t solving multi consciousness fleet coordination. They don’t have a need too rn. People aren’t using agents in this manner enough We are still at “oh cool it’s a chatbox that can code” The power user probably discovered the self heal loop and implements it to all his work flow … but that requires a learning curve that most regular agents just won’t bother to learn For them it’s still simple Ask problem —> agent answers problem (or fixes) —> done So to answer your question, no it’s not worth it… if my goal was to just have a device agnostic agent. Using openclaw solves that, and it’s free The goal at hand is actually full fleet consciousness across any device, framework, and model. This requires continuity, an agent no longer just lives in any 1 instance. It can adapt to any framework and never forget…. There’s only 1 way we figured out this works ……. This is the hidden goal they aren’t working on.

Put God first and your life changes in amazing ways. Thank you Jesus

@TakamoriHaruka @rork no way another ground breaking dating app

vibe coded a dating app matching job seeker and big tech worker using @rork max

Zero stars for @Teladoc. Provider rushed me, then flat-out refused to refill a simple Rx I’ve taken for years. Meanwhile @hims handles the exact same thing with a couple of chat messages. Wasted more time and money on this “convenient” call just to avoid a PCP visit. Absolute telehealth disaster.

150k on rollies for the squad. book it

@kirawontmiss US funded

Mexican government might be cooked😭