DA-Leclerc

@nickmalster @bradmillscan @nvk me too!

@bradmillscan @nvk I would like to know how you did this

Anyone create a Claude plugin that calls grok via api to query X yet?

@DylanLeClair @bradmillscan Using my subsidized Anthropic tokens to power my claw agents ftw

@bradmillscan Claude cowork works great for most everything you want to build and is much more cost effective because Anthropic subsidizes the tokens so it's materially cheaper

If you have activity bias, ADHD or anything resembling OCD, OpenClaw is a terrible drug and productivity poison. After 40 days in the trenches with this thing, my life is measurably worse. OpenClaw is a lot like crypto trading, gambling or playing video games. Most ppl are going to lose, and you’re going to feel like shit when you’re done - likely only 1% of ppl will find it additive to their lives. I am in a constant state of stress. I’m skipping workouts, my vision is fucked from 12-15 hrs a day on screens, my forearms are fucked from too much typing. There’s a never-ending maze of rabbit holes to fall down, footguns to step on and moles to whack. Plus when you finally do get it going, you start projects and don’t finish them because half way through something breaks. I’m not hitting the gym as often as I should, not eating right and I’ve completely lost sight of my goals and why I started in the first place. The idea of OpenClaw is so compelling and it’s very exciting when I get glimpses of what the future is going to be like when this is not a patchwork of chaos. This tech is dangerous. I know I said this last week but I need to take a break … I’m burnt out from all the constant debugging and errors across every fucking surface of this thing. It’s like trying to fly a plane without a license … oh and it’s on fire…and you’re on crack.

@bradmillscan Build it!

here's the 1 shot of the HTML page. Still, pretty damn impressive. I adding things slowly over 5 prompts giving random ideas like: "scan our continuous improvement process and then re-score everyting on the bars based on our logs." "on each of the cards, can you have the third line actuall be scrlling through relevant related items. Liek for the shuttlebay instead of listing the regression numbers, can you have the actual regressions scrolling across that card" Every designer's dream, working with an idea guy...OpenClaw handles it very well surprisingly!

I asked my OpenClaw to look at our conversation history and make a Star Trek Mission Control you'd see on a starship bridge. He one-shotted this LCARS complete with animations, interactive cards with PADD style status boxes, everything tied to the actual data on the Mac.

@zeromiedoooo @trq212 And now you can touch glass

@trq212 Bro i just want to touch grass 😭😭😭

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

@JTLonsdale What a gay post

Balaji is a bright guy but he fled the USA and has set his mind totally against our future success. He lives in a world where US is losing and China is winning. This is his fixation. It’s dangerous, and it’s wrong. And this war has embarrassed China, destroyed their 100 cargo planes of war materials and their military ally, and frustrates them. It’s fair to disagree about the attack. But saying that its architects are guilty of any downside is childlike nonsense. They should be proud of their work and their courage to take on this evil. If you’re against the war, do you get credit for the last two decades of literal mass torture and mass rape and repression by this regime, and its terror funding and death around the region? Do you get credit for “supporting” the billions it spends on social media bots and information operations to polarize the US against ourselves, and weaken the west? Do you also get credit for what would have been the next twenty years of that? Are you, Balaji, responsible for that side of it? No? But if you are for it, you get zero credit for fixing any of that, but blamed for ALL the possible downsides? Total BS. The mullahs holding the region hostage shouldn’t get your help to blame others for the damage they do. Geopolitics and war is complex and there are risks on all sides. There is risk in acting, and in not acting. I’m really glad we are taking advantage of the massive innovation and competence gap that exists at this moment, and finally eliminating so much evil. I hope for freedom for the Iranian people and know that the situation is hard and complex, but either way it is good to stop the bad guys and eliminate so many of the worst groups, who have done so much damage, from history. Nobody should get away with what those bastards did for so long; this was long overdue.

@bradmillscan Great idea! Keep us posted!

If you have ADHD + OpenClaw this is mandatory Finally took the plunge with my 🦞 to setup telegram topics. In a few days I'll know if it's making things worse or better. The idea is you can keep sessions cleaner by focusing your conversations in 1 context window/1 session.

@myscifi @johann_sath Bah, fuck em. Just went ahead and put my api in. My agents are now running on a mix of opus and sonnet. As long as it's for personal use I'm thinking I won't get banned.

@JB_Cartier @johann_sath I too am wondering this. I think people are just lying? I dont understand why I see this sentiment so much but then when I look into it it seems to not be the case

if you want to use openclaw without burning money avoid these mistakes: 1. don't pay per use on the anthropic console. get claude max ($100/month). flat rate. 2. don't run 8 agents. one agent with proper skills beats a squad of confused ones every time. 3. don't leave SOUL.md and USER.md empty. your agent sounds like a call centre without them. fill them out day 4. install QMD before you start chatting. if you add it halfway through, your agent resets and loses chat logs. 5. set up groq on day 1 (free). talking to your agent with voice notes while you're on the move changes everything.

@johann_sath @grok will anthropic allow someone to add their claude oauth to be used with an openclaw agent?

the full openclaw setup nobody explains: 1. get a VPS ($5/month hetzner or any linux box) 2. install node 18+ 3. npm install -g openclaw 4. openclaw onboard (follow the wizard) 5. connect telegram as your chat interface 6. create 3 files in your workspace: SOUL.md → personality & rules AGENTS.md → how it operates & uses memory USER.md → who you are & what you do 7. add claude max oauth ($0 API costs) 8. set up 3 cron jobs: → morning briefing (calendar + email + priorities) → evening CRM review (pipeline updates) → git backup every 2 hours that's it. 30 minutes. now you have an AI employee that knows your business, runs 24/7, and messages you on telegram.

@TSLAshareholder I actually cancelled FSD because of this. And it also doesn't work well for me during winter months with all the salt they put on the roads here, camera's always getting blocked and kicking me out.

why this do nothing?

@Crypto_Mags Can't wait to start mine up!

It has never been easier to self custody your own LLM

@hyperonline I wear mostly merino underwear and t-shirts next to skin. Don't need antiperspirant or deodorant.

- Not wearing deodorant because you are 11 and have no hormones - Wearing deodorant because you are 14 and have hormones now - Wearing natural deodorant because you are 18 now and learned that real deodorant has aluminum, which absorbs into your skin and turns you into a beautiful woman - Not wearing deodorant because you are a freshman in college who learned that splashing Tito’s Vodka on your armpits daily kills the bacteria too - Wearing natural (but homemade) deodorant because you are a junior in college and now that you’re buying alcohol for yourself you realize there is no reason to ever purchase Tito’s. But you are still too broke to pay ten dollars per stick, so you make it yourself like a freak - Wearing no deodorant because you graduated and got a nice remote job that doesn’t require you to ever shower, groom or leave the house - Wearing expensive natural deodorant because you suddenly realized you are 27 now, and if you don’t leave the house to find a wife soon it may be over - Wearing real deodorant with the aluminum that makes you a woman again because you are still single at 32 and worry finding love as a man is impossible now

@EvanWritesOnX Sounds like cope, but you could be right

Ok so to answer this. The report that Khamenei’s son-in-law and daughter-in-law were killed came from an Iranian domestic source. If you’re the Iranian state trying to rally domestic support around the “martyrdom” of the Supreme Leader, you don’t just announce he died in a strike. You announce that his family died with him. Innocents. A daughter-in-law. It transforms a military decapitation into a national tragedy. It makes the man who spent 36 years as a divisive autocratic figure into a sympathetic martyr whose family was murdered by foreign aggressors. An alternative reading is that Israel genuinely killed his family members. The strike reportedly involved 30 bombs on Khamenei’s compound. If he was underground at the location, anyone in or near that compound was going to die. Israel wouldn’t have known or cared who else was in the building. The family could simply be collateral. My personal opinion. Khamenei knew this strike was coming. The man had a four-layered succession plan prepared. He’d appointed Larijani as de facto leader weeks ago. He’d had the assembly of experts preparing for succession since before the 12 war. Iranian state media confirmed he was “at his office within his residence” when the strike hit. He was transferred to a “secure location” according to one Iranian official, then declared dead hours later. An 86-year-old man who has spent months preparing for his own assassination, who has contingency plans for every military and governmental role four layers deep, who moved his de facto authority to Larijani weeks ago… and he didn’t move his family out of the compound? Either Iranian security is catastrophically incompetent, unlikely given the level of preparation documented, or the family casualties are being reported for effect. There’s a third option too. That Khamenei wasn’t in the compound at all. The strike hit the building. The state confirmed his death hours later. But the only proof of death is Iran’s own announcement. No body has been shown. No funeral has been announced yet. Trump and Netanyahu played along. If Khamenei was already dying, he was 86, with reported health issues going back years, or if the decision had been made to “retire” him behind the cover of a strike, then announcing family casualties adds emotional weight to a narrative that needs to be unquestionable domestically. I don’t have proof for any of these readings. But to me, a man who planned this meticulously doesn’t leave his family in the blast radius by accident. So either the family deaths are real collateral from a strike he didn’t escape in time, or they’re propaganda to sanctify the transition. I think it’s propaganda. Same line of thinking applicable to the schoolgirls. I invite debate.

@TheWeb3Patriot @BRICSinfo The weapon that character is holding is Israeli

@BRICSinfo I’m not dying for Israel 🇮🇱

JUST IN: 🇮🇱🇮🇷 Israeli military says it carried out its largest airstrike ever, hitting over 500 targets across Iran with 200 fighter jets.

@martypartymusic 💯 🔥

People I was on to Jane Street as far back as 8/3/24 - keep the pressure on.

@everestchris6 Openclaw

My OpenClaw bot runs 6 AI agents 24/7: - Finds local businesses without a website - Builds a custom demo site for them automatically - Sends outreach with the preview + payment link - Handles objections and closes the sale Most local businesses don't have a website, this system finds them, pitches them, and collects payment automatically Reply "OpenClaw" and I'll send you early access (must be following)

@ted_ryce Calories

Obesity rates are going up while Americans are eating less sugar. While butter and cheese consumption have been going up. Why do you think this happening?

@jhamel 😬

Un des plus gros risques fiscaux qui plane au dessus des investisseurs canadiens / québécois : le plafonnage des gains en CELI. Ce n'est pas "si" mais "quand"...